From ff48f5a4a0b4f6051858652db72f302792501a06 Mon Sep 17 00:00:00 2001 From: Max Krasnyansky Date: Tue, 30 Apr 2024 12:29:34 -0700 Subject: [PATCH 01/11] logging: add proper checks for clang to avoid errors and warnings with VA_ARGS --- common/log.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/common/log.h b/common/log.h index 6934c57b2225c..09fa63c2677a7 100644 --- a/common/log.h +++ b/common/log.h @@ -211,7 +211,7 @@ inline std::string log_filename_generator_impl(LogTriState multilog, const std:: #define LOG_FLF_VAL , __FILE__, __LINE__, __FUNCTION__ #else #define LOG_FLF_FMT "[%24s:%5ld][%24s] " - #define LOG_FLF_VAL , __FILE__, __LINE__, __FUNCTION__ + #define LOG_FLF_VAL , __FILE__, (long)__LINE__, __FUNCTION__ #endif #else #define LOG_FLF_FMT "%s" @@ -224,7 +224,7 @@ inline std::string log_filename_generator_impl(LogTriState multilog, const std:: #define LOG_TEE_FLF_VAL , __FILE__, __LINE__, __FUNCTION__ #else #define LOG_TEE_FLF_FMT "[%24s:%5ld][%24s] " - #define LOG_TEE_FLF_VAL , __FILE__, __LINE__, __FUNCTION__ + #define LOG_TEE_FLF_VAL , __FILE__, (long)__LINE__, __FUNCTION__ #endif #else #define LOG_TEE_FLF_FMT "%s" @@ -294,7 +294,7 @@ inline std::string log_filename_generator_impl(LogTriState multilog, const std:: // Main LOG macro. // behaves like printf, and supports arguments the exact same way. // -#ifndef _MSC_VER +#if !defined(_MSC_VER) || defined(__clang__) #define LOG(...) LOG_IMPL(__VA_ARGS__, "") #else #define LOG(str, ...) LOG_IMPL("%s" str, "", ##__VA_ARGS__, "") @@ -308,14 +308,14 @@ inline std::string log_filename_generator_impl(LogTriState multilog, const std:: // Secondary target can be changed just like LOG_TARGET // by defining LOG_TEE_TARGET // -#ifndef _MSC_VER +#if !defined(_MSC_VER) || defined(__clang__) #define LOG_TEE(...) LOG_TEE_IMPL(__VA_ARGS__, "") #else #define LOG_TEE(str, ...) LOG_TEE_IMPL("%s" str, "", ##__VA_ARGS__, "") #endif // LOG macro variants with auto endline. -#ifndef _MSC_VER +#if !defined(_MSC_VER) || defined(__clang__) #define LOGLN(...) LOG_IMPL(__VA_ARGS__, "\n") #define LOG_TEELN(...) LOG_TEE_IMPL(__VA_ARGS__, "\n") #else From 7d4695370a92fa176d4d1fa99bca01f123d46310 Mon Sep 17 00:00:00 2001 From: Max Krasnyansky Date: Tue, 30 Apr 2024 12:31:54 -0700 Subject: [PATCH 02/11] build: add CMake Presets and toolchian files for Windows ARM64 --- CMakePresets.json | 45 ++++++++++++++++++++++++++++++++++ cmake/arm64-windows-llvm.cmake | 16 ++++++++++++ cmake/arm64-windows-msvc.cmake | 6 +++++ 3 files changed, 67 insertions(+) create mode 100644 CMakePresets.json create mode 100644 cmake/arm64-windows-llvm.cmake create mode 100644 cmake/arm64-windows-msvc.cmake diff --git a/CMakePresets.json b/CMakePresets.json new file mode 100644 index 0000000000000..ad1af7eccebbd --- /dev/null +++ b/CMakePresets.json @@ -0,0 +1,45 @@ +{ + "version": 4, + "configurePresets": [ + { + "name": "base", + "hidden": true, + "generator": "Ninja", + "binaryDir": "${sourceDir}/build-${presetName}", + "cacheVariables": { + "CMAKE_EXPORT_COMPILE_COMMANDS": "ON", + "CMAKE_INSTALL_RPATH": "$ORIGIN;$ORIGIN/.." + } + }, + + { "name": "debug", "hidden": true, "cacheVariables": { "CMAKE_BUILD_TYPE": "Debug" } }, + { "name": "release", "hidden": true, "cacheVariables": { "CMAKE_BUILD_TYPE": "RelWithDebInfo" } }, + { "name": "static", "hidden": true, "cacheVariables": { "LLAMA_STATIC": "ON" } }, + + { + "name": "arm64-windows-msvc", "hidden": true, + "architecture": { "value": "arm64", "strategy": "external" }, + "toolset": { "value": "host=x86_64", "strategy": "external" }, + "cacheVariables": { + "CMAKE_TOOLCHAIN_FILE": "${sourceDir}/cmake/arm64-windows-msvc.cmake" + } + }, + + { + "name": "arm64-windows-llvm", "hidden": true, + "architecture": { "value": "arm64", "strategy": "external" }, + "toolset": { "value": "host=x86_64", "strategy": "external" }, + "cacheVariables": { + "CMAKE_TOOLCHAIN_FILE": "${sourceDir}/cmake/arm64-windows-llvm.cmake" + } + }, + + { "name": "arm64-windows-llvm-debug" , "inherits": [ "base", "arm64-windows-llvm", "debug" ] }, + { "name": "arm64-windows-llvm-release", "inherits": [ "base", "arm64-windows-llvm", "release" ] }, + { "name": "arm64-windows-llvm+static-release", "inherits": [ "base", "arm64-windows-llvm", "release", "static" ] }, + + { "name": "arm64-windows-msvc-debug" , "inherits": [ "base", "arm64-windows-msvc", "debug" ] }, + { "name": "arm64-windows-msvc-release", "inherits": [ "base", "arm64-windows-msvc", "release" ] }, + { "name": "arm64-windows-msvc+static-release", "inherits": [ "base", "arm64-windows-msvc", "release", "static" ] } + ] +} diff --git a/cmake/arm64-windows-llvm.cmake b/cmake/arm64-windows-llvm.cmake new file mode 100644 index 0000000000000..46fba65149b29 --- /dev/null +++ b/cmake/arm64-windows-llvm.cmake @@ -0,0 +1,16 @@ +set( CMAKE_SYSTEM_NAME Windows ) +set( CMAKE_SYSTEM_PROCESSOR arm64 ) + +set( target arm64-pc-windows-msvc ) + +set( CMAKE_C_COMPILER clang ) +set( CMAKE_CXX_COMPILER clang++ ) + +set( CMAKE_C_COMPILER_TARGET ${target} ) +set( CMAKE_CXX_COMPILER_TARGET ${target} ) + +set( arch_c_flags "-march=armv8.7-a -fvectorize -ffp-model=fast" ) +set( warn_c_flags "-Wno-format -Wno-unused-variable -Wno-unused-function -Wno-gnu-zero-variadic-macro-arguments" ) + +set( CMAKE_C_FLAGS_INIT "${arch_c_flags} ${warn_c_flags}" ) +set( CMAKE_CXX_FLAGS_INIT "${arch_c_flags} ${warn_c_flags}" ) diff --git a/cmake/arm64-windows-msvc.cmake b/cmake/arm64-windows-msvc.cmake new file mode 100644 index 0000000000000..c77631420ce84 --- /dev/null +++ b/cmake/arm64-windows-msvc.cmake @@ -0,0 +1,6 @@ +set( CMAKE_SYSTEM_NAME Windows ) +set( CMAKE_SYSTEM_PROCESSOR arm64 ) + +set( target arm64-pc-windows-msvc ) +set( CMAKE_C_COMPILER_TARGET ${target} ) +set( CMAKE_CXX_COMPILER_TARGET ${target} ) From 18d20c07271c4ca8d3e599f3acc9a5d7456a720b Mon Sep 17 00:00:00 2001 From: Max Krasnyansky Date: Tue, 30 Apr 2024 17:10:38 -0700 Subject: [PATCH 03/11] matmul-int8: enable matmul-int8 with MSVC and fix Clang warnings --- CMakeLists.txt | 5 ++++ ggml-quants.c | 67 ++++++++++++++++++++++++++------------------------ 2 files changed, 40 insertions(+), 32 deletions(-) diff --git a/CMakeLists.txt b/CMakeLists.txt index feb6f39d09662..8ab6a45a6a074 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -1007,6 +1007,11 @@ if (CMAKE_OSX_ARCHITECTURES STREQUAL "arm64" OR CMAKE_GENERATOR_PLATFORM_LWR STR if (GGML_COMPILER_SUPPORT_DOTPROD) add_compile_definitions(__ARM_FEATURE_DOTPROD) endif () + check_cxx_source_compiles("#include \nint main() { int8x16_t _a, _b; int32x4_t _s = vmlaq_f32(_s, _a, _b); return 0; }" GGML_COMPILER_SUPPORT_MATMUL_INT8) + if (GGML_COMPILER_SUPPORT_MATMUL_INT8) + add_compile_definitions(__ARM_FEATURE_MATMUL_INT8) + endif () + check_cxx_source_compiles("#include \nint main() { float16_t _a; float16x8_t _s = vdupq_n_f16(_a); return 0; }" GGML_COMPILER_SUPPORT_FP16_VECTOR_ARITHMETIC) if (GGML_COMPILER_SUPPORT_FP16_VECTOR_ARITHMETIC) add_compile_definitions(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) diff --git a/ggml-quants.c b/ggml-quants.c index 9e62a3f32614f..ef1fcf5fa005c 100644 --- a/ggml-quants.c +++ b/ggml-quants.c @@ -3487,10 +3487,9 @@ void ggml_vec_dot_q4_0_q8_0(int n, float * restrict s, size_t bs, const void * r #if defined(__ARM_FEATURE_MATMUL_INT8) if (nrc == 2) { const block_q4_0 * restrict vx0 = vx; - const block_q4_0 * restrict vx1 = vx + bx; - + const block_q4_0 * restrict vx1 = (const block_q4_0 *) ((const uint8_t*)vx + bx); const block_q8_0 * restrict vy0 = vy; - const block_q8_0 * restrict vy1 = vy + by; + const block_q8_0 * restrict vy1 = (const block_q8_0 *) ((const uint8_t*)vy + by); float32x4_t sumv0 = vdupq_n_f32(0.0f); @@ -3524,10 +3523,12 @@ void ggml_vec_dot_q4_0_q8_0(int n, float * restrict s, size_t bs, const void * r const int8x16_t y1_l = vld1q_s8(b_y1->qs); const int8x16_t y1_h = vld1q_s8(b_y1->qs + 16); - float32x4_t scale = {GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y0->d), - GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y1->d), - GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y0->d), - GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y1->d)}; + float32_t _scale[4] = { GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y0->d), + GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y1->d), + GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y0->d), + GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y1->d)}; + + float32x4_t scale = vld1q_f32(_scale); int8x16_t l0 = vreinterpretq_s8_s64(vzip1q_s64(vreinterpretq_s64_s8(x0_l), vreinterpretq_s64_s8(x1_l))); int8x16_t l1 = vreinterpretq_s8_s64(vzip2q_s64(vreinterpretq_s64_s8(x0_l), vreinterpretq_s64_s8(x1_l))); @@ -3894,9 +3895,9 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r #if defined(__ARM_FEATURE_MATMUL_INT8) if (nrc == 2) { const block_q4_1 * restrict vx0 = vx; - const block_q4_1 * restrict vx1 = vx + bx; + const block_q4_1 * restrict vx1 = (const block_q4_1 *) ((const uint8_t*)vx + bx); const block_q8_1 * restrict vy0 = vy; - const block_q8_1 * restrict vy1 = vy + by; + const block_q8_1 * restrict vy1 = (const block_q8_1 *) ((const uint8_t*)vy + by); float32x4_t sumv0 = vdupq_n_f32(0.0f); float32x4_t summs0 = vdupq_n_f32(0.0f); @@ -3907,11 +3908,11 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r const block_q8_1 * restrict b_y0 = &vy0[i]; const block_q8_1 * restrict b_y1 = &vy1[i]; - float32x4_t summs_t = {GGML_FP16_TO_FP32(b_x0->m) * GGML_FP16_TO_FP32(b_y0->s), - GGML_FP16_TO_FP32(b_x1->m) * GGML_FP16_TO_FP32(b_y0->s), - GGML_FP16_TO_FP32(b_x0->m) * GGML_FP16_TO_FP32(b_y1->s), - GGML_FP16_TO_FP32(b_x1->m) * GGML_FP16_TO_FP32(b_y1->s)}; - summs0 += summs_t; + float32_t summs_t[4] = {GGML_FP16_TO_FP32(b_x0->m) * GGML_FP16_TO_FP32(b_y0->s), + GGML_FP16_TO_FP32(b_x1->m) * GGML_FP16_TO_FP32(b_y0->s), + GGML_FP16_TO_FP32(b_x0->m) * GGML_FP16_TO_FP32(b_y1->s), + GGML_FP16_TO_FP32(b_x1->m) * GGML_FP16_TO_FP32(b_y1->s)}; + summs0 = vaddq_f32(summs0, vld1q_f32(summs_t)); const uint8x16_t m4b = vdupq_n_u8(0x0F); @@ -3931,10 +3932,11 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r const int8x16_t y1_h = vld1q_s8(b_y1->qs + 16); // mmla into int32x4_t - float32x4_t scale = {GGML_FP16_TO_FP32(b_x0->d)*b_y0->d, - GGML_FP16_TO_FP32(b_x0->d)*b_y1->d, - GGML_FP16_TO_FP32(b_x1->d)*b_y0->d, - GGML_FP16_TO_FP32(b_x1->d)*b_y1->d}; + float32_t _scale[4] = {GGML_FP16_TO_FP32(b_x0->d)*b_y0->d, + GGML_FP16_TO_FP32(b_x0->d)*b_y1->d, + GGML_FP16_TO_FP32(b_x1->d)*b_y0->d, + GGML_FP16_TO_FP32(b_x1->d)*b_y1->d}; + float32x4_t scale = vld1q_f32(_scale); int8x16_t l0 = vreinterpretq_s8_s64(vzip1q_s64(vreinterpretq_s64_s8(x0_l), vreinterpretq_s64_s8(x1_l))); int8x16_t l1 = vreinterpretq_s8_s64(vzip2q_s64(vreinterpretq_s64_s8(x0_l), vreinterpretq_s64_s8(x1_l))); @@ -3953,7 +3955,7 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r float32x4_t sumv1 = vextq_f32(sumv0, sumv0, 2); float32x4_t sumv2 = vzip1q_f32(sumv0, sumv1); - sumv2 = sumv2 + summs0; + sumv2 = vaddq_f32(sumv2, summs0); vst1_f32(s, vget_low_f32(sumv2)); vst1_f32(s + bs, vget_high_f32(sumv2)); @@ -4836,24 +4838,24 @@ void ggml_vec_dot_q8_0_q8_0(int n, float * restrict s, size_t bs, const void * r #if defined(__ARM_FEATURE_MATMUL_INT8) if (nrc == 2) { - const block_q8_0 * restrict vx0 = vx; - const block_q8_0 * restrict vx1 = vx + bx; + const block_q4_0 * restrict vx0 = vx; + const block_q4_0 * restrict vx1 = (const block_q4_0 *) ((const uint8_t*)vx + bx); const block_q8_0 * restrict vy0 = vy; - const block_q8_0 * restrict vy1 = vy + by; + const block_q8_0 * restrict vy1 = (const block_q8_0 *) ((const uint8_t*)vy + by); float32x4_t sumv0 = vdupq_n_f32(0.0f); for (int i = 0; i < nb; i++) { - const block_q8_0 * restrict b_x0 = &vx0[i]; + const block_q4_0 * restrict b_x0 = &vx0[i]; const block_q8_0 * restrict b_y0 = &vy0[i]; - const block_q8_0 * restrict b_x1 = &vx1[i]; + const block_q4_0 * restrict b_x1 = &vx1[i]; const block_q8_0 * restrict b_y1 = &vy1[i]; - const int8x16_t x0_l = vld1q_s8(b_x0->qs); - const int8x16_t x0_h = vld1q_s8(b_x0->qs + 16); - const int8x16_t x1_l = vld1q_s8(b_x1->qs); - const int8x16_t x1_h = vld1q_s8(b_x1->qs + 16); + const int8x16_t x0_l = vld1q_s8((const int8_t*)b_x0->qs); + const int8x16_t x0_h = vld1q_s8((const int8_t*)b_x0->qs + 16); + const int8x16_t x1_l = vld1q_s8((const int8_t*)b_x1->qs); + const int8x16_t x1_h = vld1q_s8((const int8_t*)b_x1->qs + 16); // load y const int8x16_t y0_l = vld1q_s8(b_y0->qs); @@ -4861,10 +4863,11 @@ void ggml_vec_dot_q8_0_q8_0(int n, float * restrict s, size_t bs, const void * r const int8x16_t y1_l = vld1q_s8(b_y1->qs); const int8x16_t y1_h = vld1q_s8(b_y1->qs + 16); - float32x4_t scale = {GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y0->d), - GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y1->d), - GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y0->d), - GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y1->d)}; + float32_t _scale[4] = {GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y0->d), + GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y1->d), + GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y0->d), + GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y1->d)}; + float32x4_t scale = vld1q_f32(_scale); int8x16_t l0 = vreinterpretq_s8_s64(vzip1q_s64(vreinterpretq_s64_s8(x0_l), vreinterpretq_s64_s8(x1_l))); int8x16_t l1 = vreinterpretq_s8_s64(vzip2q_s64(vreinterpretq_s64_s8(x0_l), vreinterpretq_s64_s8(x1_l))); From e838a3d4595e9cfb2cb837731d76acb8413653bd Mon Sep 17 00:00:00 2001 From: Max Krasnyansky Date: Tue, 14 May 2024 20:36:57 -0700 Subject: [PATCH 04/11] ci: add support for optimized Windows ARM64 builds with MSVC and LLVM --- .github/workflows/build.yml | 61 ++++++++++++++++++++----------------- 1 file changed, 33 insertions(+), 28 deletions(-) diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index 7ac0e5f6ef15d..2d2fea4a20cc9 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -693,26 +693,28 @@ jobs: strategy: matrix: include: - - build: 'rpc' + - build: 'rpc-x64' defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_RPC=ON -DBUILD_SHARED_LIBS=ON' - - build: 'noavx' + - build: 'noavx-x64' defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DBUILD_SHARED_LIBS=ON' - - build: 'avx2' + - build: 'avx2-x64' defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' - - build: 'avx' + - build: 'avx-x64' defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SHARED_LIBS=ON' - - build: 'avx512' + - build: 'avx512-x64' defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON' - - build: 'clblast' + - build: 'clblast-x64' defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"' - - build: 'openblas' + - build: 'openblas-x64' defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"' - - build: 'kompute' + - build: 'kompute-x64' defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_KOMPUTE=ON -DKOMPUTE_OPT_DISABLE_VULKAN_VERSION_CHECK=ON -DBUILD_SHARED_LIBS=ON' - - build: 'vulkan' + - build: 'vulkan-x64' defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_VULKAN=ON -DBUILD_SHARED_LIBS=ON' - - build: 'arm64' - defines: '-A ARM64 -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + - build: 'llvm-arm64' + defines: '-G Ninja -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + - build: 'msvc-arm64' + defines: '-G Ninja -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-msvc.cmake -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' steps: - name: Clone @@ -723,13 +725,13 @@ jobs: - name: Clone Kompute submodule id: clone_kompute - if: ${{ matrix.build == 'kompute' }} + if: ${{ matrix.build == 'kompute-x64' }} run: | git submodule update --init kompute - name: Download OpenCL SDK id: get_opencl - if: ${{ matrix.build == 'clblast' }} + if: ${{ matrix.build == 'clblast-x64' }} run: | curl.exe -o $env:RUNNER_TEMP/opencl.zip -L "https://github.com/KhronosGroup/OpenCL-SDK/releases/download/v${env:OPENCL_VERSION}/OpenCL-SDK-v${env:OPENCL_VERSION}-Win-x64.zip" mkdir $env:RUNNER_TEMP/opencl @@ -737,7 +739,7 @@ jobs: - name: Download CLBlast id: get_clblast - if: ${{ matrix.build == 'clblast' }} + if: ${{ matrix.build == 'clblast-x64' }} run: | curl.exe -o $env:RUNNER_TEMP/clblast.7z -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-windows-x64.7z" curl.exe -o $env:RUNNER_TEMP/CLBlast.LICENSE.txt -L "https://github.com/CNugteren/CLBlast/raw/${env:CLBLAST_VERSION}/LICENSE" @@ -750,7 +752,7 @@ jobs: - name: Download OpenBLAS id: get_openblas - if: ${{ matrix.build == 'openblas' }} + if: ${{ matrix.build == 'openblas-x64' }} run: | curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip" curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE" @@ -763,38 +765,41 @@ jobs: - name: Install Vulkan SDK id: get_vulkan - if: ${{ matrix.build == 'kompute' || matrix.build == 'vulkan' }} + if: ${{ matrix.build == 'kompute-x64' || matrix.build == 'vulkan-x64' }} run: | curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/VulkanSDK-${env:VULKAN_VERSION}-Installer.exe" & "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}" Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin" + - name: Install Ninja + id: install_ninja + run: | + choco install ninja + - name: Build id: cmake_build run: | - mkdir build - cd build - cmake .. ${{ matrix.defines }} - cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS} + cmake -S . -B build ${{ matrix.defines }} + cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS} - name: Add clblast.dll id: add_clblast_dll - if: ${{ matrix.build == 'clblast' }} + if: ${{ matrix.build == 'clblast-x64' }} run: | cp $env:RUNNER_TEMP/clblast/lib/clblast.dll ./build/bin/Release cp $env:RUNNER_TEMP/CLBlast.LICENSE.txt ./build/bin/Release/CLBlast-${env:CLBLAST_VERSION}.txt - name: Add libopenblas.dll id: add_libopenblas_dll - if: ${{ matrix.build == 'openblas' }} + if: ${{ matrix.build == 'openblas-x64' }} run: | cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt - name: Check AVX512F support id: check_avx512f - if: ${{ matrix.build == 'avx512' }} + if: ${{ matrix.build == 'avx512-x64' }} continue-on-error: true run: | cd build @@ -808,14 +813,14 @@ jobs: - name: Test id: cmake_test # not all machines have native AVX-512 - if: ${{ matrix.build != 'arm64' && matrix.build != 'clblast' && matrix.build != 'kompute' && matrix.build != 'vulkan' && (matrix.build != 'avx512' || env.HAS_AVX512F == '1') }} + if: ${{ matrix.build != 'msvc-arm64' && matrix.build != 'llvm-arm64' && matrix.build != 'clblast-x64' && matrix.build != 'kompute-x64' && matrix.build != 'vulkan-x64' && (matrix.build != 'avx512-x64' || env.HAS_AVX512F == '1') }} run: | cd build ctest -L main -C Release --verbose --timeout 900 - name: Test (Intel SDE) id: cmake_test_sde - if: ${{ matrix.build == 'avx512' && env.HAS_AVX512F == '0' }} # use Intel SDE for AVX-512 emulation + if: ${{ matrix.build == 'avx512-x64' && env.HAS_AVX512F == '0' }} # use Intel SDE for AVX-512 emulation run: | curl.exe -o $env:RUNNER_TEMP/sde.tar.xz -L "https://downloadmirror.intel.com/813591/sde-external-${env:SDE_VERSION}-win.tar.xz" # for some weird reason windows tar doesn't like sde tar.xz @@ -843,14 +848,14 @@ jobs: if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} run: | Copy-Item LICENSE .\build\bin\Release\llama.cpp.txt - 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\* + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}.zip .\build\bin\Release\* - name: Upload artifacts if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} uses: actions/upload-artifact@v4 with: - path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip - name: llama-bin-win-${{ matrix.build }}-x64.zip + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}.zip + name: llama-bin-win-${{ matrix.build }}.zip windows-latest-cmake-cuda: runs-on: windows-latest From 397801476e53c95470f113e78fc606edd5790f37 Mon Sep 17 00:00:00 2001 From: Max Krasnyansky Date: Sun, 12 May 2024 20:24:21 -0700 Subject: [PATCH 05/11] matmul-int8: fixed typos in q8_0_q8_0 matmuls Co-authored-by: Georgi Gerganov --- ggml-quants.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/ggml-quants.c b/ggml-quants.c index ef1fcf5fa005c..e9b24f5eb81fa 100644 --- a/ggml-quants.c +++ b/ggml-quants.c @@ -4838,18 +4838,18 @@ void ggml_vec_dot_q8_0_q8_0(int n, float * restrict s, size_t bs, const void * r #if defined(__ARM_FEATURE_MATMUL_INT8) if (nrc == 2) { - const block_q4_0 * restrict vx0 = vx; - const block_q4_0 * restrict vx1 = (const block_q4_0 *) ((const uint8_t*)vx + bx); + const block_q8_0 * restrict vx0 = vx; + const block_q8_0 * restrict vx1 = (const block_q8_0 *) ((const uint8_t*)vx + bx); const block_q8_0 * restrict vy0 = vy; const block_q8_0 * restrict vy1 = (const block_q8_0 *) ((const uint8_t*)vy + by); float32x4_t sumv0 = vdupq_n_f32(0.0f); for (int i = 0; i < nb; i++) { - const block_q4_0 * restrict b_x0 = &vx0[i]; + const block_q8_0 * restrict b_x0 = &vx0[i]; const block_q8_0 * restrict b_y0 = &vy0[i]; - const block_q4_0 * restrict b_x1 = &vx1[i]; + const block_q8_0 * restrict b_x1 = &vx1[i]; const block_q8_0 * restrict b_y1 = &vy1[i]; const int8x16_t x0_l = vld1q_s8((const int8_t*)b_x0->qs); From ece01fc2e99570f240ecc9a65f3e4f3df216e827 Mon Sep 17 00:00:00 2001 From: Max Krasnyansky Date: Wed, 15 May 2024 09:05:07 -0700 Subject: [PATCH 06/11] matmul-int8: remove unnecessary casts in q8_0_q8_0 --- ggml-quants.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/ggml-quants.c b/ggml-quants.c index e9b24f5eb81fa..f13599f6b41bc 100644 --- a/ggml-quants.c +++ b/ggml-quants.c @@ -4852,10 +4852,10 @@ void ggml_vec_dot_q8_0_q8_0(int n, float * restrict s, size_t bs, const void * r const block_q8_0 * restrict b_x1 = &vx1[i]; const block_q8_0 * restrict b_y1 = &vy1[i]; - const int8x16_t x0_l = vld1q_s8((const int8_t*)b_x0->qs); - const int8x16_t x0_h = vld1q_s8((const int8_t*)b_x0->qs + 16); - const int8x16_t x1_l = vld1q_s8((const int8_t*)b_x1->qs); - const int8x16_t x1_h = vld1q_s8((const int8_t*)b_x1->qs + 16); + const int8x16_t x0_l = vld1q_s8(b_x0->qs); + const int8x16_t x0_h = vld1q_s8(b_x0->qs + 16); + const int8x16_t x1_l = vld1q_s8(b_x1->qs); + const int8x16_t x1_h = vld1q_s8(b_x1->qs + 16); // load y const int8x16_t y0_l = vld1q_s8(b_y0->qs); From f8532d62a6e89c8789955ff87f884a17e59c28f4 Mon Sep 17 00:00:00 2001 From: Esra Korkmaz Date: Thu, 10 Apr 2025 10:15:17 +0300 Subject: [PATCH 07/11] Update arm64-windows-llvm.cmake --- cmake/arm64-windows-llvm.cmake | 63 +++++++++++++++++++++++++++++++++- 1 file changed, 62 insertions(+), 1 deletion(-) diff --git a/cmake/arm64-windows-llvm.cmake b/cmake/arm64-windows-llvm.cmake index 46fba65149b29..c2ece861b1411 100644 --- a/cmake/arm64-windows-llvm.cmake +++ b/cmake/arm64-windows-llvm.cmake @@ -1,15 +1,76 @@ set( CMAKE_SYSTEM_NAME Windows ) +set( CMAKE_SYSTEM_VERSION 10.0 ) + +set( CMAKE_SYSTEM_PROCESSOR arm64 ) +set( CMAKE_SYSTEM_PROCESSOR arm64 ) +set( CMAKE_SYSTEM_PROCESSOR arm64 ) set( CMAKE_SYSTEM_PROCESSOR arm64 ) +set( CMAKE_SYSTEM_PROCESSOR arm64 ) + set( target arm64-pc-windows-msvc ) +set( CMAKE_CROSSCOMPILING TRUE ) +set( CMAKE_CROSSCOMPILING_EMULATOR "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_ID "Clang" ) +set( CMAKE_CXX_COMPILER_ID "Clang" ) +set( CMAKE_C_COMPILER_VERSION 17.0.0 ) +set( CMAKE_CXX_COMPILER_VERSION 17.0.0 ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) + + set( CMAKE_C_COMPILER clang ) +set( CMAKE_CXX_COMPILER clang++ ) +set( CMAKE_C_COMPILER_ID "Clang" ) +set( CMAKE_CXX_COMPILER_ID "Clang" ) +set( CMAKE_C_COMPILER_VERSION 17.0.0 ) +set( CMAKE_CXX_COMPILER_VERSION 17.0.0 ) +set( CMAKE_C_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_CXX_COMPILER_LAUNCHER "C:/Program Files/LLVM/bin/clang-cl.exe" ) +set( CMAKE_C_COMPILER clang ) +set( CMAKE_CXX_COMPILER clang++ ) +set( CMAKE_C_COMPILER_ID "Clang" ) +set( CMAKE_CXX_COMPILER_ID "Clang" ) set( CMAKE_CXX_COMPILER clang++ ) set( CMAKE_C_COMPILER_TARGET ${target} ) set( CMAKE_CXX_COMPILER_TARGET ${target} ) -set( arch_c_flags "-march=armv8.7-a -fvectorize -ffp-model=fast" ) +set( arch_c_flags "-march=armv8.7-a -fvectorize -ffp-model=fast -fno-finite-math-only" ) set( warn_c_flags "-Wno-format -Wno-unused-variable -Wno-unused-function -Wno-gnu-zero-variadic-macro-arguments" ) set( CMAKE_C_FLAGS_INIT "${arch_c_flags} ${warn_c_flags}" ) From 8b5f3e9a0e4ad7c4940d2189ad6d1fb3be96f7f1 Mon Sep 17 00:00:00 2001 From: Esra Korkmaz <157255418+esrakorkmz@users.noreply.github.com> Date: Fri, 11 Apr 2025 02:54:54 +0300 Subject: [PATCH 08/11] Commit --- .circleci/config.yml | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 .circleci/config.yml diff --git a/.circleci/config.yml b/.circleci/config.yml new file mode 100644 index 0000000000000..43ede34c4a6c0 --- /dev/null +++ b/.circleci/config.yml @@ -0,0 +1,26 @@ +version: 2.1 + +jobs: + test: + docker: + - image: cimg/node:16.8.0-browsers + steps: + - checkout + - restore_cache: + keys: + - node-deps-{{ checksum "package-lock.json" }} + - run: + name: Install Dependencies + command: npm install + - save_cache: + key: node-deps-{{ checksum "package-lock.json" }} + paths: + - node_modules + - run: + name: Run Tests + command: npm test + +workflows: + test-flow: + jobs: + - test From f0338fd20cd4425458a80fd7e2c66e938937f056 Mon Sep 17 00:00:00 2001 From: Esra Korkmaz Date: Sat, 12 Apr 2025 03:03:43 +0300 Subject: [PATCH 09/11] Refactor workflow inputs for CI dispatch and push triggers - Merged workflow inputs for 'create_release' and 'push' under a unified structure - Improved readability and consistency of CI trigger settings - Ensures boolean type consistency and adds support for future input expansion --- .github/workflows/Untitled-1.txt | 1812 ++++++++++++++++++++++++++++++ .github/workflows/Untitled-2.txt | 1811 +++++++++++++++++++++++++++++ .github/workflows/Untitled-3.py | 23 + .github/workflows/Untitled-3.txt | 1812 ++++++++++++++++++++++++++++++ .github/workflows/Untitled-4.txt | 1812 ++++++++++++++++++++++++++++++ .github/workflows/Untitled-5.txt | 1812 ++++++++++++++++++++++++++++++ .github/workflows/Untitled-6.txt | 1812 ++++++++++++++++++++++++++++++ .github/workflows/Untitled-7.txt | 1812 ++++++++++++++++++++++++++++++ .github/workflows/Untitled-8.txt | 1812 ++++++++++++++++++++++++++++++ .github/workflows/Untitled-9.txt | 1811 +++++++++++++++++++++++++++++ .github/workflows/build.yml | 1 + .gitignore | 2 + CMakePresets.json | 141 +-- Untitled-1.json | 14 + 14 files changed, 16361 insertions(+), 126 deletions(-) create mode 100644 .github/workflows/Untitled-1.txt create mode 100644 .github/workflows/Untitled-2.txt create mode 100644 .github/workflows/Untitled-3.py create mode 100644 .github/workflows/Untitled-3.txt create mode 100644 .github/workflows/Untitled-4.txt create mode 100644 .github/workflows/Untitled-5.txt create mode 100644 .github/workflows/Untitled-6.txt create mode 100644 .github/workflows/Untitled-7.txt create mode 100644 .github/workflows/Untitled-8.txt create mode 100644 .github/workflows/Untitled-9.txt create mode 100644 Untitled-1.json diff --git a/.github/workflows/Untitled-1.txt b/.github/workflows/Untitled-1.txt new file mode 100644 index 0000000000000..9b1372449225d --- /dev/null +++ b/.github/workflows/Untitled-1.txt @@ -0,0 +1,1812 @@ +name: CI +description: | + This workflow builds and tests the llama.cpp project on various platforms. + It is triggered on push, pull request, or manually via workflow_dispatch. + It also creates a release when a new commit is pushed to the master branch or when manually triggered. + The workflow includes jobs for macOS, Linux, and Windows, with different configurations and dependencies. + The workflow uses concurrency to cancel in-progress jobs if a new commit is pushed to the same branch. + It uses ccache to speed up the build process by caching compiled files. + +on: + workflow_dispatch: # allows manual triggering + inputs: + create_release: + default: false + description: 'Create new release' + required: true + type: boolean + push: + branches: + - master + paths: ['.github/workflows/build.yml', '.github/workflows/build-linux-cross.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + pull_request: + types: [opened, synchronize, reopened] + paths: ['.github/workflows/build.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +# Fine-grant permission +# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token +permissions: + contents: write # for creating release + +env: + BRANCH_NAME: ${{ github.head_ref || github.ref_name }} + GGML_NLOOP: 3 + GGML_N_THREADS: 1 + LLAMA_LOG_COLORS: 1 + LLAMA_LOG_PREFIX: 1 + LLAMA_LOG_TIMESTAMPS: 1 + CREATE_RELEASE: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' }} + +jobs: + macOS-latest-cmake-arm64: + runs-on: macos-14 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-arm64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: "${{ github.event_name == 'workflow_dispatch' ? github.event.inputs.create_release == 'true' : github.ref == 'refs/heads/master' }}" + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip + name: llama-bin-macos-arm64.zip + + macOS-latest-cmake-x64: + runs-on: macos-13 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-x64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + # Metal is disabled due to intermittent failures with Github runners not having a GPU: + # https://github.com/ggml-org/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313 + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL=OFF \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip + name: llama-bin-macos-x64.zip + + ubuntu-cpu-cmake: + strategy: + matrix: + include: + - build: 'x64' + os: ubuntu-22.04 + - build: 'arm64' + os: ubuntu-22.04-arm + + runs-on: ${{ matrix.os }} + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-cpu-cmake + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Test llama2c conversion + id: llama2c_test + run: | + cd build + echo "Fetch tokenizer" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin + echo "Fetch llama2c model" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin + ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf + ./bin/llama-cli -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip + name: llama-bin-ubuntu-${{ matrix.build }}.zip + + ubuntu-latest-cmake-sanitizer: + runs-on: ubuntu-latest + + continue-on-error: true + + strategy: + matrix: + sanitizer: [ADDRESS, THREAD, UNDEFINED] + build_type: [Debug] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-sanitizer-${{ matrix.sanitizer }} + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + if: ${{ matrix.sanitizer != 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Build (no OpenMP) + id: cmake_build_no_openmp + if: ${{ matrix.sanitizer == 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \ + -DGGML_OPENMP=OFF + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-llguidance: + runs-on: ubuntu-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_LLGUIDANCE=ON + cmake --build . --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-cmake-rpc: + runs-on: ubuntu-latest + + continue-on-error: true + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-rpc + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose + + ubuntu-22-cmake-vulkan: + runs-on: ubuntu-22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-vulkan + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | sudo apt-key add - + sudo wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list + sudo apt-get update -y + sudo apt-get install -y build-essential mesa-vulkan-drivers vulkan-sdk libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_VULKAN=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + # This is using llvmpipe and runs slower than other backends + ctest -L main --verbose --timeout 2700 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip + name: llama-bin-ubuntu-vulkan-x64.zip + + ubuntu-22-cmake-hip: + runs-on: ubuntu-22.04 + container: rocm/dev-ubuntu-22.04:6.0.2 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-hip + evict-old-files: 1d + + - name: Build with native CMake HIP support + id: cmake_build + run: | + cmake -B build -S . \ + -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build --config Release -j $(nproc) + + - name: Build with legacy HIP support + id: cmake_build_legacy_hip + run: | + cmake -B build2 -S . \ + -DCMAKE_C_COMPILER=hipcc \ + -DCMAKE_CXX_COMPILER=hipcc \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build2 --config Release -j $(nproc) + + ubuntu-22-cmake-musa: + runs-on: ubuntu-22.04 + container: mthreads/musa:rc3.1.1-devel-ubuntu22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + apt-get update + apt-get install -y build-essential git cmake libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-musa + evict-old-files: 1d + + - name: Build with native CMake MUSA support + id: cmake_build + run: | + cmake -B build -S . \ + -DGGML_MUSA=ON + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl-fp16: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl-fp16 + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx \ + -DGGML_SYCL_F16=ON + cmake --build build --config Release -j $(nproc) + + build-linux-cross: + uses: ./.github/workflows/build-linux-cross.yml + + macOS-latest-cmake-ios: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-ios + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-tvos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-tvos + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=tvOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-visionos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=visionOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=1.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-swift: + runs-on: macos-latest + + strategy: + matrix: + destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-swift + evict-old-files: 1d + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build llama.cpp with CMake + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64" + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + windows-msys2: + runs-on: windows-latest + + strategy: + fail-fast: false + matrix: + include: + - { sys: UCRT64, env: ucrt-x86_64, build: Release } + - { sys: CLANG64, env: clang-x86_64, build: Release } + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-msys2 + variant: sccache + evict-old-files: 1d + + - name: Setup ${{ matrix.sys }} + uses: msys2/setup-msys2@v2 + with: + update: true + msystem: ${{matrix.sys}} + install: >- + base-devel + git + mingw-w64-${{matrix.env}}-toolchain + mingw-w64-${{matrix.env}}-cmake + mingw-w64-${{matrix.env}}-openblas + + - name: Setup for build + run: | + echo "Setting up build environment" + + - name: Build using CMake + shell: msys2 {0} + run: | + cmake -B build + cmake --build build --config ${{ matrix.build }} -j $(nproc) + + - name: Clean after building using CMake + shell: msys2 {0} + run: | + rm -rf build + + - name: Build using CMake w/ OpenBLAS + shell: msys2 {0} + run: | + cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS + cmake --build build --config ${{ matrix.build }} -j $(nproc) + # Removed duplicate environment key "CURL_PATH" from this job to avoid conflicts. + + windows-latest-cmake: + runs-on: windows-latest + + env: + OPENBLAS_VERSION: 0.3.23 + SDE_VERSION: 9.33.0-2024-01-07 + VULKAN_VERSION: 1.4.309.0 + + strategy: + matrix: + include: + - build: 'rpc' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_RPC=ON -DBUILD_SHARED_LIBS=ON' + - build: 'noavx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx2' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + - build: 'avx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx512' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON' + - build: 'clblast' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"' + - build: 'openblas' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"' + - build: 'kompute' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_KOMPUTE=ON -DKOMPUTE_OPT_DISABLE_VULKAN_VERSION_CHECK=ON -DBUILD_SHARED_LIBS=ON' + - build: 'vulkan' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_VULKAN=ON -DBUILD_SHARED_LIBS=ON' + - build: 'arm64' + defines: '-A ARM64 -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Clone Kompute submodule + id: clone_kompute + if: ${{ matrix.build == 'kompute-x64' }} + run: | + git submodule update --init kompute + + - name: Download OpenCL SDK + id: get_opencl + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/opencl.zip -L "https://github.com/KhronosGroup/OpenCL-SDK/releases/download/v${env:OPENCL_VERSION}/OpenCL-SDK-v${env:OPENCL_VERSION}-Win-x64.zip" + mkdir $env:RUNNER_TEMP/opencl + tar.exe -xvf $env:RUNNER_TEMP/opencl.zip --strip-components=1 -C $env:RUNNER_TEMP/opencl + + - name: Download CLBlast + id: get_clblast + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/clblast.7z -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-windows-x64.7z" + curl.exe -o $env:RUNNER_TEMP/CLBlast.LICENSE.txt -L "https://github.com/CNugteren/CLBlast/raw/${env:CLBLAST_VERSION}/LICENSE" + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/clblast.7z + rename-item $env:RUNNER_TEMP/CLBlast-${env:CLBLAST_VERSION}-windows-x64 clblast + foreach ($f in (gci -Recurse -Path "$env:RUNNER_TEMP/clblast" -Filter '*.cmake')) { + $txt = Get-Content -Path $f -Raw + $txt.Replace('C:/vcpkg/packages/opencl_x64-windows/', "$($env:RUNNER_TEMP.Replace('\','/'))/opencl/") | Set-Content -Path $f -Encoding UTF8 + } + + - name: Download OpenBLAS + id: get_openblas + if: ${{ matrix.build == 'openblas-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip" + curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE" + mkdir $env:RUNNER_TEMP/openblas + tar.exe -xvf $env:RUNNER_TEMP/openblas.zip -C $env:RUNNER_TEMP/openblas + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $lib = $(join-path $msvc 'bin\Hostx64\x64\lib.exe') + & $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll + + - name: Install Vulkan SDK + id: get_vulkan + if: ${{ matrix.build == 'kompute-x64' || matrix.build == 'vulkan-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/VulkanSDK-${env:VULKAN_VERSION}-Installer.exe" + & "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install + Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}" + Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin" + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. ${{ matrix.defines }} + cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS} + + - name: Add clblast.dll + id: add_clblast_dll + if: ${{ matrix.build == 'clblast' }} + run: | + git clone https://github.com/KhronosGroup/OpenCL-Headers + cd OpenCL-Headers + cmake -B build ` + -DBUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build --target install + git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader + cd OpenCL-ICD-Loader + cmake -B build-arm64-release ` + -A arm64 ` + -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build-arm64-release --target install --config release + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Copy libcurl DLL + id: copy_curl_dll + run: | + cp $env:RUNNER_TEMP/curl/bin/libcurl-x64.dll ./build/bin/Release/libcurl-x64.dll + + - name: Add libopenblas.dll + id: add_libopenblas_dll + if: ${{ matrix.build == 'openblas-x64' }} + run: | + cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll + cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt + + - name: Check AVX512F support + id: check_avx512f + if: ${{ matrix.build == 'avx512-x64' }} + continue-on-error: true + run: | + cd build + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $cl = $(join-path $msvc 'bin\Hostx64\x64\cl.exe') + echo 'int main(void){unsigned int a[4];__cpuid(a,7);return !(a[1]&65536);}' >> avx512f.c + & $cl /O2 /GS- /kernel avx512f.c /link /nodefaultlib /entry:main + .\avx512f.exe && echo "AVX512F: YES" && ( echo HAS_AVX512F=1 >> $env:GITHUB_ENV ) || echo "AVX512F: NO" + + - name: Test + id: cmake_test + # not all machines have native AVX-512 + if: ${{ matrix.build != 'arm64' && matrix.build != 'clblast' && matrix.build != 'kompute' && matrix.build != 'vulkan' && (matrix.build != 'avx512' || steps.check_avx512f.outputs.has_avx512f == '1') }} + run: | + cd build + ctest -L main -C Release --verbose --timeout 900 + + - name: Test (Intel SDE) + if: ${{ matrix.build == 'avx512-x64' && (steps.check_avx512f.outputs.has_avx512f == '0') }} # use Intel SDE for AVX-512 emulation + if: ${{ matrix.build == 'avx512-x64' && env.HAS_AVX512F == '0' }} # use Intel SDE for AVX-512 emulation + run: | + curl.exe -o $env:RUNNER_TEMP/sde.tar.xz -L "https://downloadmirror.intel.com/813591/sde-external-${env:SDE_VERSION}-win.tar.xz" + # for some weird reason windows tar doesn't like sde tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar + $sde = $(join-path $env:RUNNER_TEMP sde-external-${env:SDE_VERSION}-win/sde.exe) + cd build + $env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1 + & $sde -future -- ctest -L main -C Release --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + Copy-Item LICENSE .\build\bin\Release\llama.cpp.txt + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip + name: llama-bin-win-${{ matrix.build }}-x64.zip + + windows-latest-cmake-cuda: + runs-on: windows-latest + + strategy: + matrix: + cuda: ['12.4', '11.7'] + build: ['cuda'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }}-${{ matrix.cuda }}-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Install Cuda Toolkit 11.7 + if: ${{ matrix.cuda == '11.7' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-11.7.4.6-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-11.7.101-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-11.7.91-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cudart-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvcc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvrtc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libcublas-windows-x86_64-11.7.4.6-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvtx-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\visual_studio_integration-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvprof-windows-x86_64-11.7.101-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cccl-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V11_7=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Cuda Toolkit 12.4 + if: ${{ matrix.cuda == '12.4' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-12.4.131-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-12.4.5.8-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-12.4.127-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cudart-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvcc-windows-x86_64-12.4.131-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvrtc-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libcublas-windows-x86_64-12.4.5.8-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvtx-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_profiler_api-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\visual_studio_integration-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvprof-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cccl-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V12_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Ninja + id: install_ninja + run: | + choco install ninja + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\Release\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip + name: llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + - name: Copy and pack Cuda runtime + if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + run: | + echo "Cuda install location: ${{ env.CUDA_PATH }}" + $dst='.\build\bin\cudart\' + robocopy "${{env.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + robocopy "${{env.CUDA_PATH}}\lib" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + 7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip $dst\* + + - name: Upload Cuda runtime + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + name: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + windows-latest-cmake-sycl: + runs-on: windows-latest + + defaults: + run: + shell: bash + + env: + WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b380d914-366b-4b77-a74a-05e3c38b3514/intel-oneapi-base-toolkit-2025.0.0.882_offline.exe + WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel + ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI" + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-sycl + variant: sccache + evict-old-files: 1d + + - name: Install + run: | + scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL + + # TODO: add libcurl support ; we will also need to modify win-build-sycl.bat to accept user-specified args + + - name: Build + id: cmake_build + run: examples/sycl/win-build-sycl.bat + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Build the release package + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + run: | + echo "cp oneAPI running time dll files in ${{ env.ONEAPI_ROOT }} to ./build/bin" + + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_sycl_blas.5.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_core.2.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_tbb_thread.2.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_opencl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_loader.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_win_proxy_loader.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl8.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/svml_dispmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libmmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libiomp5md.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/dnnl/latest/bin/dnnl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/tbb/latest/bin/tbb12.dll" ./build/bin + + echo "cp oneAPI running time dll files to ./build/bin done" + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip ./build/bin/* + + - name: Upload the release package + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip + name: llama-bin-win-sycl-x64.zip + + windows-latest-cmake-hip: + if: ${{ github.event.inputs.create_release != 'true' }} + runs-on: windows-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }} + evict-old-files: 1d + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DGGML_HIP=ON ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + + # TODO: reuse windows-latest-cmake-hip instead of duplicating this job + windows-latest-cmake-hip-release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + runs-on: windows-latest + + strategy: + matrix: + gpu_target: [gfx1100, gfx1101, gfx1030] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-hip-release + evict-old-files: 1d + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DAMDGPU_TARGETS=${{ matrix.gpu_target }} ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_HIP=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + md "build\bin\rocblas\library\" + cp "${env:HIP_PATH}\bin\hipblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas\library\*" "build\bin\rocblas\library\" + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip .\build\bin\* + + - name: Upload artifacts + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + name: llama-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + + ios-xcode-build: + runs-on: macos-latest + + steps: + - name: Checkout code + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + - name: Build Xcode project + run: xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + run: | + zip --symlinks -r llama-${{ steps.tag.outputs.name }}-xcframework.zip build-apple/llama.xcframework + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-xcframework.zip + name: llama-${{ steps.tag.outputs.name }}-xcframework + + android-build: + runs-on: ubuntu-latest + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: android-build + evict-old-files: 1d + + - name: Set up JDK + uses: actions/setup-java@v3 + with: + java-version: 17 + distribution: zulu + + - name: Setup Android SDK + uses: android-actions/setup-android@v3 + with: + log-accepted-android-sdk-licenses: false + + - name: Build + run: | + cd examples/llama.android + + ./gradlew build --no-daemon + + release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + + runs-on: ubuntu-latest + + needs: + - ubuntu-cpu-cmake + - ubuntu-22-cmake-vulkan + - windows-latest-cmake + - windows-latest-cmake-cuda + - windows-latest-cmake-sycl + - windows-latest-cmake-hip-release + - macOS-latest-cmake-arm64 + - macOS-latest-cmake-x64 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: release + evict-old-files: 1d + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Download artifacts + id: download-artifact + uses: actions/download-artifact@v4 + with: + path: ./artifact + + - name: Move artifacts + id: move_artifacts + run: mkdir -p ./artifact/release && mv ./artifact/*/*.zip ./artifact/release + + - name: Create release + id: create_release + uses: ggml-org/action-create-release@v1 + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + with: + tag_name: ${{ steps.tag.outputs.name }} + + - name: Upload release + id: upload_release + uses: actions/github-script@v3 + with: + github-token: ${{secrets.GITHUB_TOKEN}} + script: | + const path = require('path'); + const fs = require('fs'); + const release_id = '${{ steps.create_release.outputs.id }}'; + for (let file of await fs.readdirSync('./artifact/release')) { + if (path.extname(file) === '.zip') { + console.log('uploadReleaseAsset', file); + await github.repos.uploadReleaseAsset({ + owner: context.repo.owner, + repo: context.repo.repo, + release_id: release_id, + name: file, + data: await fs.readFileSync(`./artifact/release/${file}`) + }); + } + } + +# ubuntu-latest-gcc: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-clang: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_COMPILER=clang +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-gcc-sanitized: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# sanitizer: [ADDRESS, THREAD, UNDEFINED] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=Debug -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON +# +# - name: Build +# run: | +# make +# +# windows: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# include: +# - arch: Win32 +# s2arc: x86 +# - arch: x64 +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Upload binaries +# uses: actions/upload-artifact@v4 +# with: +# name: llama-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# windows-blas: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# blas: [ON] +# include: +# - arch: Win32 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x86.zip +# s2arc: x86 +# - arch: x64 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x64.zip +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Fetch OpenBLAS +# if: matrix.blas == 'ON' +# run: | +# C:/msys64/usr/bin/wget.exe -qO blas.zip ${{ matrix.obzip }} +# 7z x blas.zip -oblas -y +# copy blas/include/cblas.h . +# copy blas/include/openblas_config.h . +# echo "blasdir=$env:GITHUB_WORKSPACE/blas" >> $env:GITHUB_ENV +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# -DLLAMA_SUPPORT_OPENBLAS=${{ matrix.blas }} +# -DCMAKE_LIBRARY_PATH="$env:blasdir/lib" +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Copy libopenblas.dll +# if: matrix.blas == 'ON' +# run: copy "$env:blasdir/bin/libopenblas.dll" build/bin/${{ matrix.build }} +# +# - name: Upload binaries +# if: matrix.blas == 'ON' +# uses: actions/upload-artifact@v4 +# with: +# name: llama-blas-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# emscripten: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# wget -q https://github.com/emscripten-core/emsdk/archive/master.tar.gz +# tar -xvf master.tar.gz +# emsdk-master/emsdk update +# emsdk-master/emsdk install latest +# emsdk-master/emsdk activate latest +# +# - name: Configure +# run: echo "tmp" +# +# - name: Build +# run: | +# pushd emsdk-master +# source ./emsdk_env.sh +# popd +# emcmake cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# make + + openEuler-latest-cmake-cann: + if: ${{ github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'Ascend NPU') }} + defaults: + run: + shell: bash -el {0} + runs-on: ubuntu-24.04-arm + strategy: + matrix: + cann: + - '8.1.RC1.alpha001-910b-openeuler22.03-py3.10' + device: + - 'ascend910b3' + build: + - 'Release' + container: ascendai/cann:${{ matrix.cann }} + steps: + - name: Checkout + uses: actions/checkout@v4 + + - name: Dependencies + run: | + yum update -y + yum install -y git gcc gcc-c++ make cmake libcurl-devel + + - name: Build + run: | + export LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/$(uname -m)-linux/devlib/:${LD_LIBRARY_PATH} + + cmake -S . -B build \ + -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ + -DGGML_CANN=on \ + -DSOC_TYPE=${{ matrix.device }} + cmake --build build -j $(nproc) diff --git a/.github/workflows/Untitled-2.txt b/.github/workflows/Untitled-2.txt new file mode 100644 index 0000000000000..271a07164e5d5 --- /dev/null +++ b/.github/workflows/Untitled-2.txt @@ -0,0 +1,1811 @@ +name: CI +description: | + This workflow builds and tests the llama.cpp project on various platforms. + It is triggered on push, pull request, or manually via workflow_dispatch. + It also creates a release when a new commit is pushed to the master branch or when manually triggered. + The workflow includes jobs for macOS, Linux, and Windows, with different configurations and dependencies. + The workflow uses concurrency to cancel in-progress jobs if a new commit is pushed to the same branch. + It uses ccache to speed up the build process by caching compiled files. + +on: + workflow_dispatch: # allows manual triggering + inputs: + create_release: + default: false + description: 'Create new release' + required: true + type: boolean + push: + branches: + - master + paths: ['.github/workflows/build.yml', '.github/workflows/build-linux-cross.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + pull_request: + types: [opened, synchronize, reopened] + paths: ['.github/workflows/build.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +# Fine-grant permission +# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token +permissions: + contents: write # for creating release + +env: + BRANCH_NAME: ${{ github.head_ref || github.ref_name }} + GGML_NLOOP: 3 + GGML_N_THREADS: 1 + LLAMA_LOG_COLORS: 1 + LLAMA_LOG_PREFIX: 1 + LLAMA_LOG_TIMESTAMPS: 1 + CREATE_RELEASE: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' }} + +jobs: + macOS-latest-cmake-arm64: + runs-on: macos-14 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-arm64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ (github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true') || github.ref == 'refs/heads/master' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip + name: llama-bin-macos-arm64.zip + + macOS-latest-cmake-x64: + runs-on: macos-13 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-x64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + # Metal is disabled due to intermittent failures with Github runners not having a GPU: + # https://github.com/ggml-org/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313 + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL=OFF \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip + name: llama-bin-macos-x64.zip + + ubuntu-cpu-cmake: + strategy: + matrix: + include: + - build: 'x64' + os: ubuntu-22.04 + - build: 'arm64' + os: ubuntu-22.04-arm + + runs-on: ${{ matrix.os }} + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-cpu-cmake + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Test llama2c conversion + id: llama2c_test + run: | + cd build + echo "Fetch tokenizer" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin + echo "Fetch llama2c model" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin + ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf + ./bin/llama-cli -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip + name: llama-bin-ubuntu-${{ matrix.build }}.zip + + ubuntu-latest-cmake-sanitizer: + runs-on: ubuntu-latest + + continue-on-error: true + + strategy: + matrix: + sanitizer: [ADDRESS, THREAD, UNDEFINED] + build_type: [Debug] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-sanitizer-${{ matrix.sanitizer }} + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + if: ${{ matrix.sanitizer != 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Build (no OpenMP) + id: cmake_build_no_openmp + if: ${{ matrix.sanitizer == 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \ + -DGGML_OPENMP=OFF + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-llguidance: + runs-on: ubuntu-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_LLGUIDANCE=ON + cmake --build . --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-cmake-rpc: + runs-on: ubuntu-latest + + continue-on-error: true + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-rpc + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose + + ubuntu-22-cmake-vulkan: + runs-on: ubuntu-22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-vulkan + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | sudo apt-key add - + sudo wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list + sudo apt-get update -y + sudo apt-get install -y build-essential mesa-vulkan-drivers vulkan-sdk libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_VULKAN=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + # This is using llvmpipe and runs slower than other backends + ctest -L main --verbose --timeout 2700 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip + name: llama-bin-ubuntu-vulkan-x64.zip + + ubuntu-22-cmake-hip: + runs-on: ubuntu-22.04 + container: rocm/dev-ubuntu-22.04:6.0.2 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-hip + evict-old-files: 1d + + - name: Build with native CMake HIP support + id: cmake_build + run: | + cmake -B build -S . \ + -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build --config Release -j $(nproc) + + - name: Build with legacy HIP support + id: cmake_build_legacy_hip + run: | + cmake -B build2 -S . \ + -DCMAKE_C_COMPILER=hipcc \ + -DCMAKE_CXX_COMPILER=hipcc \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build2 --config Release -j $(nproc) + + ubuntu-22-cmake-musa: + runs-on: ubuntu-22.04 + container: mthreads/musa:rc3.1.1-devel-ubuntu22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + apt-get update + apt-get install -y build-essential git cmake libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-musa + evict-old-files: 1d + + - name: Build with native CMake MUSA support + id: cmake_build + run: | + cmake -B build -S . \ + -DGGML_MUSA=ON + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl-fp16: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl-fp16 + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx \ + -DGGML_SYCL_F16=ON + cmake --build build --config Release -j $(nproc) + + build-linux-cross: + uses: ./.github/workflows/build-linux-cross.yml + + macOS-latest-cmake-ios: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-ios + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-tvos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-tvos + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=tvOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-visionos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=visionOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=1.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-swift: + runs-on: macos-latest + + strategy: + matrix: + destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-swift + evict-old-files: 1d + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build llama.cpp with CMake + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64" + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + windows-msys2: + runs-on: windows-latest + + strategy: + fail-fast: false + matrix: + include: + - { sys: UCRT64, env: ucrt-x86_64, build: Release } + - { sys: CLANG64, env: clang-x86_64, build: Release } + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-msys2 + variant: sccache + evict-old-files: 1d + + - name: Setup ${{ matrix.sys }} + uses: msys2/setup-msys2@v2 + with: + update: true + msystem: ${{matrix.sys}} + install: >- + base-devel + git + mingw-w64-${{matrix.env}}-toolchain + mingw-w64-${{matrix.env}}-cmake + mingw-w64-${{matrix.env}}-openblas + + - name: Setup for build + run: | + echo "Setting up build environment" + + - name: Build using CMake + shell: msys2 {0} + run: | + cmake -B build + cmake --build build --config ${{ matrix.build }} -j $(nproc) + + - name: Clean after building using CMake + shell: msys2 {0} + run: | + rm -rf build + + - name: Build using CMake w/ OpenBLAS + shell: msys2 {0} + run: | + cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS + cmake --build build --config ${{ matrix.build }} -j $(nproc) + # Removed duplicate environment key "CURL_PATH" from this job to avoid conflicts. + + windows-latest-cmake: + runs-on: windows-latest + + env: + OPENBLAS_VERSION: 0.3.23 + SDE_VERSION: 9.33.0-2024-01-07 + VULKAN_VERSION: 1.4.309.0 + + strategy: + matrix: + include: + - build: 'rpc' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_RPC=ON -DBUILD_SHARED_LIBS=ON' + - build: 'noavx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx2' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + - build: 'avx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx512' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON' + - build: 'clblast' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"' + - build: 'openblas' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"' + - build: 'kompute' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_KOMPUTE=ON -DKOMPUTE_OPT_DISABLE_VULKAN_VERSION_CHECK=ON -DBUILD_SHARED_LIBS=ON' + - build: 'vulkan' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_VULKAN=ON -DBUILD_SHARED_LIBS=ON' + - build: 'arm64' + defines: '-A ARM64 -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Clone Kompute submodule + id: clone_kompute + if: ${{ matrix.build == 'kompute-x64' }} + run: | + git submodule update --init kompute + + - name: Download OpenCL SDK + id: get_opencl + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/opencl.zip -L "https://github.com/KhronosGroup/OpenCL-SDK/releases/download/v${env:OPENCL_VERSION}/OpenCL-SDK-v${env:OPENCL_VERSION}-Win-x64.zip" + mkdir $env:RUNNER_TEMP/opencl + tar.exe -xvf $env:RUNNER_TEMP/opencl.zip --strip-components=1 -C $env:RUNNER_TEMP/opencl + + - name: Download CLBlast + id: get_clblast + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/clblast.7z -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-windows-x64.7z" + curl.exe -o $env:RUNNER_TEMP/CLBlast.LICENSE.txt -L "https://github.com/CNugteren/CLBlast/raw/${env:CLBLAST_VERSION}/LICENSE" + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/clblast.7z + rename-item $env:RUNNER_TEMP/CLBlast-${env:CLBLAST_VERSION}-windows-x64 clblast + foreach ($f in (gci -Recurse -Path "$env:RUNNER_TEMP/clblast" -Filter '*.cmake')) { + $txt = Get-Content -Path $f -Raw + $txt.Replace('C:/vcpkg/packages/opencl_x64-windows/', "$($env:RUNNER_TEMP.Replace('\','/'))/opencl/") | Set-Content -Path $f -Encoding UTF8 + } + + - name: Download OpenBLAS + id: get_openblas + if: ${{ matrix.build == 'openblas-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip" + curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE" + mkdir $env:RUNNER_TEMP/openblas + tar.exe -xvf $env:RUNNER_TEMP/openblas.zip -C $env:RUNNER_TEMP/openblas + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $lib = $(join-path $msvc 'bin\Hostx64\x64\lib.exe') + & $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll + + - name: Install Vulkan SDK + id: get_vulkan + if: ${{ matrix.build == 'kompute-x64' || matrix.build == 'vulkan-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/VulkanSDK-${env:VULKAN_VERSION}-Installer.exe" + & "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install + Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}" + Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin" + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. ${{ matrix.defines }} + cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS} + + - name: Add clblast.dll + id: add_clblast_dll + if: ${{ matrix.build == 'clblast' }} + run: | + git clone https://github.com/KhronosGroup/OpenCL-Headers + cd OpenCL-Headers + cmake -B build ` + -DBUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build --target install + git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader + cd OpenCL-ICD-Loader + cmake -B build-arm64-release ` + -A arm64 ` + -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build-arm64-release --target install --config release + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build with libCURL + id: cmake_build_curl + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Copy libcurl DLL + id: copy_curl_dll + run: | + cp $env:RUNNER_TEMP/curl/bin/libcurl-x64.dll ./build/bin/Release/libcurl-x64.dll + + - name: Add libopenblas.dll + id: add_libopenblas_dll + if: ${{ matrix.build == 'openblas-x64' }} + run: | + cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll + cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt + + - name: Check AVX512F support + id: check_avx512f + if: ${{ matrix.build == 'avx512-x64' }} + continue-on-error: true + run: | + cd build + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $cl = $(join-path $msvc 'bin\Hostx64\x64\cl.exe') + echo 'int main(void){unsigned int a[4];__cpuid(a,7);return !(a[1]&65536);}' >> avx512f.c + & $cl /O2 /GS- /kernel avx512f.c /link /nodefaultlib /entry:main + .\avx512f.exe && echo "AVX512F: YES" && ( echo HAS_AVX512F=1 >> $env:GITHUB_ENV ) || echo "AVX512F: NO" + + - name: Test + id: cmake_test + # not all machines have native AVX-512 + if: ${{ matrix.build != 'arm64' && matrix.build != 'clblast' && matrix.build != 'kompute' && matrix.build != 'vulkan' && (matrix.build != 'avx512' || steps.check_avx512f.outputs.has_avx512f == '1') }} + run: | + cd build + ctest -L main -C Release --verbose --timeout 900 + + - name: Test (Intel SDE) + if: ${{ matrix.build == 'avx512-x64' && steps.check_avx512f.outputs.has_avx512f == '0' }} # use Intel SDE for AVX-512 emulation + run: | + curl.exe -o $env:RUNNER_TEMP/sde.tar.xz -L "https://downloadmirror.intel.com/813591/sde-external-${env:SDE_VERSION}-win.tar.xz" + # for some weird reason windows tar doesn't like sde tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar + $sde = $(join-path $env:RUNNER_TEMP sde-external-${env:SDE_VERSION}-win/sde.exe) + cd build + $env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1 + & $sde -future -- ctest -L main -C Release --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + Copy-Item LICENSE .\build\bin\Release\llama.cpp.txt + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip + name: llama-bin-win-${{ matrix.build }}-x64.zip + + windows-latest-cmake-cuda: + runs-on: windows-latest + + strategy: + matrix: + cuda: ['12.4', '11.7'] + build: ['cuda'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }}-${{ matrix.cuda }}-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Install Cuda Toolkit 11.7 + if: ${{ matrix.cuda == '11.7' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-11.7.4.6-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-11.7.101-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-11.7.91-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cudart-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvcc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvrtc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libcublas-windows-x86_64-11.7.4.6-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvtx-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\visual_studio_integration-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvprof-windows-x86_64-11.7.101-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cccl-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V11_7=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Cuda Toolkit 12.4 + if: ${{ matrix.cuda == '12.4' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-12.4.131-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-12.4.5.8-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-12.4.127-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cudart-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvcc-windows-x86_64-12.4.131-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvrtc-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libcublas-windows-x86_64-12.4.5.8-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvtx-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_profiler_api-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\visual_studio_integration-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvprof-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cccl-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V12_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Ninja + id: install_ninja + run: | + choco install ninja + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\Release\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip + name: llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + - name: Copy and pack Cuda runtime + if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + run: | + echo "Cuda install location: $CUDA_PATH" + $dst='.\build\bin\cudart\' + robocopy "$env:CUDA_PATH\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + robocopy "$env:CUDA_PATH\lib" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + 7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip $dst\* + + - name: Upload Cuda runtime + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + name: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + windows-latest-cmake-sycl: + runs-on: windows-latest + + defaults: + run: + shell: bash + + env: + WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b380d914-366b-4b77-a74a-05e3c38b3514/intel-oneapi-base-toolkit-2025.0.0.882_offline.exe + WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel + ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI" + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-sycl + variant: sccache + evict-old-files: 1d + + - name: Install + run: | + scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL + + # TODO: add libcurl support ; we will also need to modify win-build-sycl.bat to accept user-specified args + + - name: Build + id: cmake_build + run: examples/sycl/win-build-sycl.bat + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Build the release package + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + echo "cp oneAPI running time dll files in ${{ env.ONEAPI_ROOT }} to ./build/bin" + + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_sycl_blas.5.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_core.2.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_tbb_thread.2.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_opencl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_loader.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_win_proxy_loader.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl8.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/svml_dispmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libmmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libiomp5md.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/dnnl/latest/bin/dnnl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/tbb/latest/bin/tbb12.dll" ./build/bin + + echo "cp oneAPI running time dll files to ./build/bin done" + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip ./build/bin/* + + - name: Upload the release package + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip + name: llama-bin-win-sycl-x64.zip + + windows-latest-cmake-hip: + if: ${{ github.event.inputs.create_release != 'true' }} + runs-on: windows-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }} + evict-old-files: 1d + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DGGML_HIP=ON ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + + # TODO: reuse windows-latest-cmake-hip instead of duplicating this job + windows-latest-cmake-hip-release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + runs-on: windows-latest + + strategy: + matrix: + gpu_target: [gfx1100, gfx1101, gfx1030] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-hip-release + evict-old-files: 1d + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DAMDGPU_TARGETS=${{ matrix.gpu_target }} ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_HIP=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + md "build\bin\rocblas\library\" + cp "${env:HIP_PATH}\bin\hipblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas\library\*" "build\bin\rocblas\library\" + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip .\build\bin\* + + - name: Upload artifacts + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + name: llama-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + + ios-xcode-build: + runs-on: macos-latest + + steps: + - name: Checkout code + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + - name: Build Xcode project + run: xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + zip --symlinks -r llama-${{ steps.tag.outputs.name }}-xcframework.zip build-apple/llama.xcframework + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-xcframework.zip + name: llama-${{ steps.tag.outputs.name }}-xcframework + + android-build: + runs-on: ubuntu-latest + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: android-build + evict-old-files: 1d + + - name: Set up JDK + uses: actions/setup-java@v3 + with: + java-version: 17 + distribution: zulu + + - name: Setup Android SDK + uses: android-actions/setup-android@v3 + with: + log-accepted-android-sdk-licenses: false + + - name: Build + run: | + cd examples/llama.android + + ./gradlew build --no-daemon + + release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + + runs-on: ubuntu-latest + + needs: + - ubuntu-cpu-cmake + - ubuntu-22-cmake-vulkan + - windows-latest-cmake + - windows-latest-cmake-cuda + - windows-latest-cmake-sycl + - windows-latest-cmake-hip-release + - macOS-latest-cmake-arm64 + - macOS-latest-cmake-x64 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: release + evict-old-files: 1d + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Download artifacts + id: download-artifact + uses: actions/download-artifact@v4 + with: + path: ./artifact + + - name: Move artifacts + id: move_artifacts + run: mkdir -p ./artifact/release && mv ./artifact/*/*.zip ./artifact/release + + - name: Create release + id: create_release + uses: ggml-org/action-create-release@v1 + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + with: + tag_name: ${{ steps.tag.outputs.name }} + + - name: Upload release + id: upload_release + uses: actions/github-script@v3 + with: + github-token: ${{secrets.GITHUB_TOKEN}} + script: | + const path = require('path'); + const fs = require('fs'); + const release_id = '${{ steps.create_release.outputs.id }}'; + for (let file of await fs.readdirSync('./artifact/release')) { + if (path.extname(file) === '.zip') { + console.log('uploadReleaseAsset', file); + await github.repos.uploadReleaseAsset({ + owner: context.repo.owner, + repo: context.repo.repo, + release_id: release_id, + name: file, + data: await fs.readFileSync(`./artifact/release/${file}`) + }); + } + } + +# ubuntu-latest-gcc: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-clang: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_COMPILER=clang +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-gcc-sanitized: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# sanitizer: [ADDRESS, THREAD, UNDEFINED] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=Debug -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON +# +# - name: Build +# run: | +# make +# +# windows: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# include: +# - arch: Win32 +# s2arc: x86 +# - arch: x64 +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Upload binaries +# uses: actions/upload-artifact@v4 +# with: +# name: llama-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# windows-blas: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# blas: [ON] +# include: +# - arch: Win32 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x86.zip +# s2arc: x86 +# - arch: x64 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x64.zip +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Fetch OpenBLAS +# if: matrix.blas == 'ON' +# run: | +# C:/msys64/usr/bin/wget.exe -qO blas.zip ${{ matrix.obzip }} +# 7z x blas.zip -oblas -y +# copy blas/include/cblas.h . +# copy blas/include/openblas_config.h . +# echo "blasdir=$env:GITHUB_WORKSPACE/blas" >> $env:GITHUB_ENV +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# -DLLAMA_SUPPORT_OPENBLAS=${{ matrix.blas }} +# -DCMAKE_LIBRARY_PATH="$env:blasdir/lib" +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Copy libopenblas.dll +# if: matrix.blas == 'ON' +# run: copy "$env:blasdir/bin/libopenblas.dll" build/bin/${{ matrix.build }} +# +# - name: Upload binaries +# if: matrix.blas == 'ON' +# uses: actions/upload-artifact@v4 +# with: +# name: llama-blas-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# emscripten: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# wget -q https://github.com/emscripten-core/emsdk/archive/master.tar.gz +# tar -xvf master.tar.gz +# emsdk-master/emsdk update +# emsdk-master/emsdk install latest +# emsdk-master/emsdk activate latest +# +# - name: Configure +# run: echo "tmp" +# +# - name: Build +# run: | +# pushd emsdk-master +# source ./emsdk_env.sh +# popd +# emcmake cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# make + + openEuler-latest-cmake-cann: + if: ${{ github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'Ascend NPU') }} + defaults: + run: + shell: bash -el {0} + runs-on: ubuntu-24.04-arm + strategy: + matrix: + cann: + - '8.1.RC1.alpha001-910b-openeuler22.03-py3.10' + device: + - 'ascend910b3' + build: + - 'Release' + container: ascendai/cann:${{ matrix.cann }} + steps: + - name: Checkout + uses: actions/checkout@v4 + + - name: Dependencies + run: | + yum update -y + yum install -y git gcc gcc-c++ make cmake libcurl-devel + + - name: Build + run: | + export LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/$(uname -m)-linux/devlib/:${LD_LIBRARY_PATH} + + cmake -S . -B build \ + -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ + -DGGML_CANN=on \ + -DSOC_TYPE=${{ matrix.device }} + cmake --build build -j $(nproc) diff --git a/.github/workflows/Untitled-3.py b/.github/workflows/Untitled-3.py new file mode 100644 index 0000000000000..29678d8b3324f --- /dev/null +++ b/.github/workflows/Untitled-3.py @@ -0,0 +1,23 @@ +def hello_world(): + """Prints 'Hello, World!' to the console.""" + # This is a simple function that prints a message + # to the console. It demonstrates the use of a function + # in Python. + # The function does not take any arguments and does not return anything. + # It simply executes the print statement when called. + # The message is a common example used in programming tutorials. + # The function is defined using the 'def' keyword followed by the function name + # and parentheses. The body of the function is indented. + # The print function is a built-in function in Python that outputs text to the console. + # In this case, it outputs the string "Hello, World!". + # The string is enclosed in double quotes, but single quotes could also be used. + # The function can be called by using its name followed by parentheses. + # This will execute the code inside the function and display the message. + # The function can be called multiple times to print the message again. + print("Hello, World!") + +# Call the function to execute it and print the message +hello_world() # Output: Hello, world! +# Call the function to execute it and print the message + +hello_world() \ No newline at end of file diff --git a/.github/workflows/Untitled-3.txt b/.github/workflows/Untitled-3.txt new file mode 100644 index 0000000000000..89d80294c375e --- /dev/null +++ b/.github/workflows/Untitled-3.txt @@ -0,0 +1,1812 @@ +name: CI +description: | + This workflow builds and tests the llama.cpp project on various platforms. + It is triggered on push, pull request, or manually via workflow_dispatch. + It also creates a release when a new commit is pushed to the master branch or when manually triggered. + The workflow includes jobs for macOS, Linux, and Windows, with different configurations and dependencies. + The workflow uses concurrency to cancel in-progress jobs if a new commit is pushed to the same branch. + It uses ccache to speed up the build process by caching compiled files. + +on: + workflow_dispatch: # allows manual triggering + inputs: + create_release: + default: false + description: 'Create new release' + required: true + type: boolean + push: + branches: + - master + paths: ['.github/workflows/build.yml', '.github/workflows/build-linux-cross.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + pull_request: + types: [opened, synchronize, reopened] + paths: ['.github/workflows/build.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +# Fine-grant permission +# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token +permissions: + contents: write # for creating release + +env: + BRANCH_NAME: ${{ github.head_ref || github.ref_name }} + GGML_NLOOP: 3 + GGML_N_THREADS: 1 + LLAMA_LOG_COLORS: 1 + LLAMA_LOG_PREFIX: 1 + LLAMA_LOG_TIMESTAMPS: 1 + CREATE_RELEASE: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' }} + +jobs: + macOS-latest-cmake-arm64: + runs-on: macos-14 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-arm64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: "${{ github.event_name == 'workflow_dispatch' ? github.event.inputs.create_release == 'true' : github.ref == 'refs/heads/master' }}" + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip + name: llama-bin-macos-arm64.zip + + macOS-latest-cmake-x64: + runs-on: macos-13 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-x64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + # Metal is disabled due to intermittent failures with Github runners not having a GPU: + # https://github.com/ggml-org/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313 + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL=OFF \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip + name: llama-bin-macos-x64.zip + + ubuntu-cpu-cmake: + strategy: + matrix: + include: + - build: 'x64' + os: ubuntu-22.04 + - build: 'arm64' + os: ubuntu-22.04-arm + + runs-on: ${{ matrix.os }} + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-cpu-cmake + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Test llama2c conversion + id: llama2c_test + run: | + cd build + echo "Fetch tokenizer" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin + echo "Fetch llama2c model" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin + ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf + ./bin/llama-cli -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip + name: llama-bin-ubuntu-${{ matrix.build }}.zip + + ubuntu-latest-cmake-sanitizer: + runs-on: ubuntu-latest + + continue-on-error: true + + strategy: + matrix: + sanitizer: [ADDRESS, THREAD, UNDEFINED] + build_type: [Debug] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-sanitizer-${{ matrix.sanitizer }} + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + if: ${{ matrix.sanitizer != 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Build (no OpenMP) + id: cmake_build_no_openmp + if: ${{ matrix.sanitizer == 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \ + -DGGML_OPENMP=OFF + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-llguidance: + runs-on: ubuntu-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_LLGUIDANCE=ON + cmake --build . --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-cmake-rpc: + runs-on: ubuntu-latest + + continue-on-error: true + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-rpc + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose + + ubuntu-22-cmake-vulkan: + runs-on: ubuntu-22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-vulkan + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | sudo apt-key add - + sudo wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list + sudo apt-get update -y + sudo apt-get install -y build-essential mesa-vulkan-drivers vulkan-sdk libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_VULKAN=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + # This is using llvmpipe and runs slower than other backends + ctest -L main --verbose --timeout 2700 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip + name: llama-bin-ubuntu-vulkan-x64.zip + + ubuntu-22-cmake-hip: + runs-on: ubuntu-22.04 + container: rocm/dev-ubuntu-22.04:6.0.2 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-hip + evict-old-files: 1d + + - name: Build with native CMake HIP support + id: cmake_build + run: | + cmake -B build -S . \ + -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build --config Release -j $(nproc) + + - name: Build with legacy HIP support + id: cmake_build_legacy_hip + run: | + cmake -B build2 -S . \ + -DCMAKE_C_COMPILER=hipcc \ + -DCMAKE_CXX_COMPILER=hipcc \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build2 --config Release -j $(nproc) + + ubuntu-22-cmake-musa: + runs-on: ubuntu-22.04 + container: mthreads/musa:rc3.1.1-devel-ubuntu22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + apt-get update + apt-get install -y build-essential git cmake libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-musa + evict-old-files: 1d + + - name: Build with native CMake MUSA support + id: cmake_build + run: | + cmake -B build -S . \ + -DGGML_MUSA=ON + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl-fp16: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl-fp16 + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx \ + -DGGML_SYCL_F16=ON + cmake --build build --config Release -j $(nproc) + + build-linux-cross: + uses: ./.github/workflows/build-linux-cross.yml + + macOS-latest-cmake-ios: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-ios + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-tvos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-tvos + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=tvOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-visionos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=visionOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=1.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-swift: + runs-on: macos-latest + + strategy: + matrix: + destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-swift + evict-old-files: 1d + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build llama.cpp with CMake + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64" + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + windows-msys2: + runs-on: windows-latest + + strategy: + fail-fast: false + matrix: + include: + - { sys: UCRT64, env: ucrt-x86_64, build: Release } + - { sys: CLANG64, env: clang-x86_64, build: Release } + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-msys2 + variant: sccache + evict-old-files: 1d + + - name: Setup ${{ matrix.sys }} + uses: msys2/setup-msys2@v2 + with: + update: true + msystem: ${{matrix.sys}} + install: >- + base-devel + git + mingw-w64-${{matrix.env}}-toolchain + mingw-w64-${{matrix.env}}-cmake + mingw-w64-${{matrix.env}}-openblas + + - name: Setup for build + run: | + echo "Setting up build environment" + + - name: Build using CMake + shell: msys2 {0} + run: | + cmake -B build + cmake --build build --config ${{ matrix.build }} -j $(nproc) + + - name: Clean after building using CMake + shell: msys2 {0} + run: | + rm -rf build + + - name: Build using CMake w/ OpenBLAS + shell: msys2 {0} + run: | + cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS + cmake --build build --config ${{ matrix.build }} -j $(nproc) + # Removed duplicate environment key "CURL_PATH" from this job to avoid conflicts. + + windows-latest-cmake: + runs-on: windows-latest + + env: + OPENBLAS_VERSION: 0.3.23 + SDE_VERSION: 9.33.0-2024-01-07 + VULKAN_VERSION: 1.4.309.0 + + strategy: + matrix: + include: + - build: 'rpc' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_RPC=ON -DBUILD_SHARED_LIBS=ON' + - build: 'noavx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx2' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + - build: 'avx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx512' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON' + - build: 'clblast' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"' + - build: 'openblas' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"' + - build: 'kompute' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_KOMPUTE=ON -DKOMPUTE_OPT_DISABLE_VULKAN_VERSION_CHECK=ON -DBUILD_SHARED_LIBS=ON' + - build: 'vulkan' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_VULKAN=ON -DBUILD_SHARED_LIBS=ON' + - build: 'arm64' + defines: '-A ARM64 -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Clone Kompute submodule + id: clone_kompute + if: ${{ matrix.build == 'kompute-x64' }} + run: | + git submodule update --init kompute + + - name: Download OpenCL SDK + id: get_opencl + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/opencl.zip -L "https://github.com/KhronosGroup/OpenCL-SDK/releases/download/v${env:OPENCL_VERSION}/OpenCL-SDK-v${env:OPENCL_VERSION}-Win-x64.zip" + mkdir $env:RUNNER_TEMP/opencl + tar.exe -xvf $env:RUNNER_TEMP/opencl.zip --strip-components=1 -C $env:RUNNER_TEMP/opencl + + - name: Download CLBlast + id: get_clblast + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/clblast.7z -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-windows-x64.7z" + curl.exe -o $env:RUNNER_TEMP/CLBlast.LICENSE.txt -L "https://github.com/CNugteren/CLBlast/raw/${env:CLBLAST_VERSION}/LICENSE" + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/clblast.7z + rename-item $env:RUNNER_TEMP/CLBlast-${env:CLBLAST_VERSION}-windows-x64 clblast + foreach ($f in (gci -Recurse -Path "$env:RUNNER_TEMP/clblast" -Filter '*.cmake')) { + $txt = Get-Content -Path $f -Raw + $txt.Replace('C:/vcpkg/packages/opencl_x64-windows/', "$($env:RUNNER_TEMP.Replace('\','/'))/opencl/") | Set-Content -Path $f -Encoding UTF8 + } + + - name: Download OpenBLAS + id: get_openblas + if: ${{ matrix.build == 'openblas-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip" + curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE" + mkdir $env:RUNNER_TEMP/openblas + tar.exe -xvf $env:RUNNER_TEMP/openblas.zip -C $env:RUNNER_TEMP/openblas + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $lib = $(join-path $msvc 'bin\Hostx64\x64\lib.exe') + & $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll + + - name: Install Vulkan SDK + id: get_vulkan + if: ${{ matrix.build == 'kompute-x64' || matrix.build == 'vulkan-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/VulkanSDK-${env:VULKAN_VERSION}-Installer.exe" + & "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install + Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}" + Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin" + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. ${{ matrix.defines }} + cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS} + + - name: Add clblast.dll + id: add_clblast_dll + if: ${{ matrix.build == 'clblast' }} + run: | + git clone https://github.com/KhronosGroup/OpenCL-Headers + cd OpenCL-Headers + cmake -B build ` + -DBUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build --target install + git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader + cd OpenCL-ICD-Loader + cmake -B build-arm64-release ` + -A arm64 ` + -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build-arm64-release --target install --config release + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_curl + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Copy libcurl DLL + id: copy_curl_dll + run: | + cp $env:RUNNER_TEMP/curl/bin/libcurl-x64.dll ./build/bin/Release/libcurl-x64.dll + + - name: Add libopenblas.dll + id: add_libopenblas_dll + if: ${{ matrix.build == 'openblas-x64' }} + run: | + cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll + cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt + + - name: Check AVX512F support + id: check_avx512f + if: ${{ matrix.build == 'avx512-x64' }} + continue-on-error: true + run: | + cd build + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $cl = $(join-path $msvc 'bin\Hostx64\x64\cl.exe') + echo 'int main(void){unsigned int a[4];__cpuid(a,7);return !(a[1]&65536);}' >> avx512f.c + & $cl /O2 /GS- /kernel avx512f.c /link /nodefaultlib /entry:main + .\avx512f.exe && echo "AVX512F: YES" && ( echo HAS_AVX512F=1 >> $env:GITHUB_ENV ) || echo "AVX512F: NO" + + - name: Test + id: cmake_test + # not all machines have native AVX-512 + if: ${{ matrix.build != 'arm64' && matrix.build != 'clblast' && matrix.build != 'kompute' && matrix.build != 'vulkan' && (matrix.build != 'avx512' || steps.check_avx512f.outputs.has_avx512f == '1') }} + run: | + cd build + ctest -L main -C Release --verbose --timeout 900 + + - name: Test (Intel SDE) + if: ${{ matrix.build == 'avx512-x64' && (steps.check_avx512f.outputs.has_avx512f == '0') }} # use Intel SDE for AVX-512 emulation + if: ${{ matrix.build == 'avx512-x64' && env.HAS_AVX512F == '0' }} # use Intel SDE for AVX-512 emulation + run: | + curl.exe -o $env:RUNNER_TEMP/sde.tar.xz -L "https://downloadmirror.intel.com/813591/sde-external-${env:SDE_VERSION}-win.tar.xz" + # for some weird reason windows tar doesn't like sde tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar + $sde = $(join-path $env:RUNNER_TEMP sde-external-${env:SDE_VERSION}-win/sde.exe) + cd build + $env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1 + & $sde -future -- ctest -L main -C Release --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + Copy-Item LICENSE .\build\bin\Release\llama.cpp.txt + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip + name: llama-bin-win-${{ matrix.build }}-x64.zip + + windows-latest-cmake-cuda: + runs-on: windows-latest + + strategy: + matrix: + cuda: ['12.4', '11.7'] + build: ['cuda'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }}-${{ matrix.cuda }}-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Install Cuda Toolkit 11.7 + if: ${{ matrix.cuda == '11.7' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-11.7.4.6-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-11.7.101-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-11.7.91-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cudart-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvcc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvrtc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libcublas-windows-x86_64-11.7.4.6-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvtx-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\visual_studio_integration-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvprof-windows-x86_64-11.7.101-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cccl-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V11_7=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Cuda Toolkit 12.4 + if: ${{ matrix.cuda == '12.4' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-12.4.131-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-12.4.5.8-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-12.4.127-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cudart-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvcc-windows-x86_64-12.4.131-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvrtc-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libcublas-windows-x86_64-12.4.5.8-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvtx-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_profiler_api-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\visual_studio_integration-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvprof-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cccl-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V12_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Ninja + id: install_ninja + run: | + choco install ninja + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_cuda + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\Release\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip + name: llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + - name: Copy and pack Cuda runtime + if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + run: | + echo "Cuda install location: ${{ env.CUDA_PATH }}" + $dst='.\build\bin\cudart\' + robocopy "${{env.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + robocopy "${{env.CUDA_PATH}}\lib" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + 7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip $dst\* + + - name: Upload Cuda runtime + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + name: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + windows-latest-cmake-sycl: + runs-on: windows-latest + + defaults: + run: + shell: bash + + env: + WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b380d914-366b-4b77-a74a-05e3c38b3514/intel-oneapi-base-toolkit-2025.0.0.882_offline.exe + WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel + ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI" + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-sycl + variant: sccache + evict-old-files: 1d + + - name: Install + run: | + scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL + + # TODO: add libcurl support ; we will also need to modify win-build-sycl.bat to accept user-specified args + + - name: Build + id: cmake_build + run: examples/sycl/win-build-sycl.bat + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Build the release package + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + echo "cp oneAPI running time dll files in ${{ env.ONEAPI_ROOT }} to ./build/bin" + + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_sycl_blas.5.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_core.2.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_tbb_thread.2.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_opencl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_loader.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_win_proxy_loader.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl8.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/svml_dispmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libmmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libiomp5md.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/dnnl/latest/bin/dnnl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/tbb/latest/bin/tbb12.dll" ./build/bin + + echo "cp oneAPI running time dll files to ./build/bin done" + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip ./build/bin/* + + - name: Upload the release package + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip + name: llama-bin-win-sycl-x64.zip + + windows-latest-cmake-hip: + if: ${{ github.event.inputs.create_release != 'true' }} + runs-on: windows-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }} + evict-old-files: 1d + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_hip + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DGGML_HIP=ON ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + + # TODO: reuse windows-latest-cmake-hip instead of duplicating this job + windows-latest-cmake-hip-release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + runs-on: windows-latest + + strategy: + matrix: + gpu_target: [gfx1100, gfx1101, gfx1030] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-hip-release + evict-old-files: 1d + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_hip_release + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DAMDGPU_TARGETS=${{ matrix.gpu_target }} ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_HIP=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + md "build\bin\rocblas\library\" + cp "${env:HIP_PATH}\bin\hipblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas\library\*" "build\bin\rocblas\library\" + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip .\build\bin\* + + - name: Upload artifacts + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + name: llama-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + + ios-xcode-build: + runs-on: macos-latest + + steps: + - name: Checkout code + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + - name: Build Xcode project + run: xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + zip --symlinks -r llama-${{ steps.tag.outputs.name }}-xcframework.zip build-apple/llama.xcframework + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-xcframework.zip + name: llama-${{ steps.tag.outputs.name }}-xcframework + + android-build: + runs-on: ubuntu-latest + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: android-build + evict-old-files: 1d + + - name: Set up JDK + uses: actions/setup-java@v3 + with: + java-version: 17 + distribution: zulu + + - name: Setup Android SDK + uses: android-actions/setup-android@v3 + with: + log-accepted-android-sdk-licenses: false + + - name: Build + run: | + cd examples/llama.android + + ./gradlew build --no-daemon + + release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + + runs-on: ubuntu-latest + + needs: + - ubuntu-cpu-cmake + - ubuntu-22-cmake-vulkan + - windows-latest-cmake + - windows-latest-cmake-cuda + - windows-latest-cmake-sycl + - windows-latest-cmake-hip-release + - macOS-latest-cmake-arm64 + - macOS-latest-cmake-x64 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: release + evict-old-files: 1d + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Download artifacts + id: download-artifact + uses: actions/download-artifact@v4 + with: + path: ./artifact + + - name: Move artifacts + id: move_artifacts + run: mkdir -p ./artifact/release && mv ./artifact/*/*.zip ./artifact/release + + - name: Create release + id: create_release + uses: ggml-org/action-create-release@v1 + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + with: + tag_name: ${{ steps.tag.outputs.name }} + + - name: Upload release + id: upload_release + uses: actions/github-script@v3 + with: + github-token: ${{secrets.GITHUB_TOKEN}} + script: | + const path = require('path'); + const fs = require('fs'); + const release_id = '${{ steps.create_release.outputs.id }}'; + for (let file of await fs.readdirSync('./artifact/release')) { + if (path.extname(file) === '.zip') { + console.log('uploadReleaseAsset', file); + await github.repos.uploadReleaseAsset({ + owner: context.repo.owner, + repo: context.repo.repo, + release_id: release_id, + name: file, + data: await fs.readFileSync(`./artifact/release/${file}`) + }); + } + } + +# ubuntu-latest-gcc: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-clang: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_COMPILER=clang +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-gcc-sanitized: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# sanitizer: [ADDRESS, THREAD, UNDEFINED] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=Debug -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON +# +# - name: Build +# run: | +# make +# +# windows: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# include: +# - arch: Win32 +# s2arc: x86 +# - arch: x64 +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Upload binaries +# uses: actions/upload-artifact@v4 +# with: +# name: llama-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# windows-blas: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# blas: [ON] +# include: +# - arch: Win32 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x86.zip +# s2arc: x86 +# - arch: x64 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x64.zip +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Fetch OpenBLAS +# if: matrix.blas == 'ON' +# run: | +# C:/msys64/usr/bin/wget.exe -qO blas.zip ${{ matrix.obzip }} +# 7z x blas.zip -oblas -y +# copy blas/include/cblas.h . +# copy blas/include/openblas_config.h . +# echo "blasdir=$env:GITHUB_WORKSPACE/blas" >> $env:GITHUB_ENV +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# -DLLAMA_SUPPORT_OPENBLAS=${{ matrix.blas }} +# -DCMAKE_LIBRARY_PATH="$env:blasdir/lib" +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Copy libopenblas.dll +# if: matrix.blas == 'ON' +# run: copy "$env:blasdir/bin/libopenblas.dll" build/bin/${{ matrix.build }} +# +# - name: Upload binaries +# if: matrix.blas == 'ON' +# uses: actions/upload-artifact@v4 +# with: +# name: llama-blas-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# emscripten: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# wget -q https://github.com/emscripten-core/emsdk/archive/master.tar.gz +# tar -xvf master.tar.gz +# emsdk-master/emsdk update +# emsdk-master/emsdk install latest +# emsdk-master/emsdk activate latest +# +# - name: Configure +# run: echo "tmp" +# +# - name: Build +# run: | +# pushd emsdk-master +# source ./emsdk_env.sh +# popd +# emcmake cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# make + + openEuler-latest-cmake-cann: + if: ${{ github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'Ascend NPU') }} + defaults: + run: + shell: bash -el {0} + runs-on: ubuntu-24.04-arm + strategy: + matrix: + cann: + - '8.1.RC1.alpha001-910b-openeuler22.03-py3.10' + device: + - 'ascend910b3' + build: + - 'Release' + container: ascendai/cann:${{ matrix.cann }} + steps: + - name: Checkout + uses: actions/checkout@v4 + + - name: Dependencies + run: | + yum update -y + yum install -y git gcc gcc-c++ make cmake libcurl-devel + + - name: Build + run: | + export LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/$(uname -m)-linux/devlib/:${LD_LIBRARY_PATH} + + cmake -S . -B build \ + -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ + -DGGML_CANN=on \ + -DSOC_TYPE=${{ matrix.device }} + cmake --build build -j $(nproc) diff --git a/.github/workflows/Untitled-4.txt b/.github/workflows/Untitled-4.txt new file mode 100644 index 0000000000000..5d7c3a8f3d337 --- /dev/null +++ b/.github/workflows/Untitled-4.txt @@ -0,0 +1,1812 @@ +name: CI +description: | + This workflow builds and tests the llama.cpp project on various platforms. + It is triggered on push, pull request, or manually via workflow_dispatch. + It also creates a release when a new commit is pushed to the master branch or when manually triggered. + The workflow includes jobs for macOS, Linux, and Windows, with different configurations and dependencies. + The workflow uses concurrency to cancel in-progress jobs if a new commit is pushed to the same branch. + It uses ccache to speed up the build process by caching compiled files. + +on: + workflow_dispatch: # allows manual triggering + inputs: + create_release: + default: false + description: 'Create new release' + required: true + type: boolean + push: + branches: + - master + paths: ['.github/workflows/build.yml', '.github/workflows/build-linux-cross.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + pull_request: + types: [opened, synchronize, reopened] + paths: ['.github/workflows/build.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +# Fine-grant permission +# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token +permissions: + contents: write # for creating release + +env: + BRANCH_NAME: ${{ github.head_ref || github.ref_name }} + GGML_NLOOP: 3 + GGML_N_THREADS: 1 + LLAMA_LOG_COLORS: 1 + LLAMA_LOG_PREFIX: 1 + LLAMA_LOG_TIMESTAMPS: 1 + CREATE_RELEASE: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' }} + +jobs: + macOS-latest-cmake-arm64: + runs-on: macos-14 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-arm64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: "${{ github.event_name == 'workflow_dispatch' ? github.event.inputs.create_release == 'true' : github.ref == 'refs/heads/master' }}" + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip + name: llama-bin-macos-arm64.zip + + macOS-latest-cmake-x64: + runs-on: macos-13 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-x64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + # Metal is disabled due to intermittent failures with Github runners not having a GPU: + # https://github.com/ggml-org/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313 + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL=OFF \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip + name: llama-bin-macos-x64.zip + + ubuntu-cpu-cmake: + strategy: + matrix: + include: + - build: 'x64' + os: ubuntu-22.04 + - build: 'arm64' + os: ubuntu-22.04-arm + + runs-on: ${{ matrix.os }} + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-cpu-cmake + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Test llama2c conversion + id: llama2c_test + run: | + cd build + echo "Fetch tokenizer" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin + echo "Fetch llama2c model" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin + ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf + ./bin/llama-cli -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip + name: llama-bin-ubuntu-${{ matrix.build }}.zip + + ubuntu-latest-cmake-sanitizer: + runs-on: ubuntu-latest + + continue-on-error: true + + strategy: + matrix: + sanitizer: [ADDRESS, THREAD, UNDEFINED] + build_type: [Debug] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-sanitizer-${{ matrix.sanitizer }} + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + if: ${{ matrix.sanitizer != 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Build (no OpenMP) + id: cmake_build_no_openmp + if: ${{ matrix.sanitizer == 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \ + -DGGML_OPENMP=OFF + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-llguidance: + runs-on: ubuntu-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_LLGUIDANCE=ON + cmake --build . --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-cmake-rpc: + runs-on: ubuntu-latest + + continue-on-error: true + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-rpc + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose + + ubuntu-22-cmake-vulkan: + runs-on: ubuntu-22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-vulkan + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | sudo apt-key add - + sudo wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list + sudo apt-get update -y + sudo apt-get install -y build-essential mesa-vulkan-drivers vulkan-sdk libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_VULKAN=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + # This is using llvmpipe and runs slower than other backends + ctest -L main --verbose --timeout 2700 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip + name: llama-bin-ubuntu-vulkan-x64.zip + + ubuntu-22-cmake-hip: + runs-on: ubuntu-22.04 + container: rocm/dev-ubuntu-22.04:6.0.2 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-hip + evict-old-files: 1d + + - name: Build with native CMake HIP support + id: cmake_build + run: | + cmake -B build -S . \ + -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build --config Release -j $(nproc) + + - name: Build with legacy HIP support + id: cmake_build_legacy_hip + run: | + cmake -B build2 -S . \ + -DCMAKE_C_COMPILER=hipcc \ + -DCMAKE_CXX_COMPILER=hipcc \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build2 --config Release -j $(nproc) + + ubuntu-22-cmake-musa: + runs-on: ubuntu-22.04 + container: mthreads/musa:rc3.1.1-devel-ubuntu22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + apt-get update + apt-get install -y build-essential git cmake libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-musa + evict-old-files: 1d + + - name: Build with native CMake MUSA support + id: cmake_build + run: | + cmake -B build -S . \ + -DGGML_MUSA=ON + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl-fp16: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl-fp16 + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx \ + -DGGML_SYCL_F16=ON + cmake --build build --config Release -j $(nproc) + + build-linux-cross: + uses: ./.github/workflows/build-linux-cross.yml + + macOS-latest-cmake-ios: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-ios + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-tvos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-tvos + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=tvOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-visionos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=visionOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=1.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-swift: + runs-on: macos-latest + + strategy: + matrix: + destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-swift + evict-old-files: 1d + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build llama.cpp with CMake + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64" + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + windows-msys2: + runs-on: windows-latest + + strategy: + fail-fast: false + matrix: + include: + - { sys: UCRT64, env: ucrt-x86_64, build: Release } + - { sys: CLANG64, env: clang-x86_64, build: Release } + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-msys2 + variant: sccache + evict-old-files: 1d + + - name: Setup ${{ matrix.sys }} + uses: msys2/setup-msys2@v2 + with: + update: true + msystem: ${{matrix.sys}} + install: >- + base-devel + git + mingw-w64-${{matrix.env}}-toolchain + mingw-w64-${{matrix.env}}-cmake + mingw-w64-${{matrix.env}}-openblas + + - name: Setup for build + run: | + echo "Setting up build environment" + + - name: Build using CMake + shell: msys2 {0} + run: | + cmake -B build + cmake --build build --config ${{ matrix.build }} -j $(nproc) + + - name: Clean after building using CMake + shell: msys2 {0} + run: | + rm -rf build + + - name: Build using CMake w/ OpenBLAS + shell: msys2 {0} + run: | + cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS + cmake --build build --config ${{ matrix.build }} -j $(nproc) + # Removed duplicate environment key "CURL_PATH" from this job to avoid conflicts. + + windows-latest-cmake: + runs-on: windows-latest + + env: + OPENBLAS_VERSION: 0.3.23 + SDE_VERSION: 9.33.0-2024-01-07 + VULKAN_VERSION: 1.4.309.0 + + strategy: + matrix: + include: + - build: 'rpc' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_RPC=ON -DBUILD_SHARED_LIBS=ON' + - build: 'noavx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx2' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + - build: 'avx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx512' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON' + - build: 'clblast' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"' + - build: 'openblas' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"' + - build: 'kompute' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_KOMPUTE=ON -DKOMPUTE_OPT_DISABLE_VULKAN_VERSION_CHECK=ON -DBUILD_SHARED_LIBS=ON' + - build: 'vulkan' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_VULKAN=ON -DBUILD_SHARED_LIBS=ON' + - build: 'arm64' + defines: '-A ARM64 -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Clone Kompute submodule + id: clone_kompute + if: ${{ matrix.build == 'kompute-x64' }} + run: | + git submodule update --init kompute + + - name: Download OpenCL SDK + id: get_opencl + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/opencl.zip -L "https://github.com/KhronosGroup/OpenCL-SDK/releases/download/v${env:OPENCL_VERSION}/OpenCL-SDK-v${env:OPENCL_VERSION}-Win-x64.zip" + mkdir $env:RUNNER_TEMP/opencl + tar.exe -xvf $env:RUNNER_TEMP/opencl.zip --strip-components=1 -C $env:RUNNER_TEMP/opencl + + - name: Download CLBlast + id: get_clblast + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/clblast.7z -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-windows-x64.7z" + curl.exe -o $env:RUNNER_TEMP/CLBlast.LICENSE.txt -L "https://github.com/CNugteren/CLBlast/raw/${env:CLBLAST_VERSION}/LICENSE" + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/clblast.7z + rename-item $env:RUNNER_TEMP/CLBlast-${env:CLBLAST_VERSION}-windows-x64 clblast + foreach ($f in (gci -Recurse -Path "$env:RUNNER_TEMP/clblast" -Filter '*.cmake')) { + $txt = Get-Content -Path $f -Raw + $txt.Replace('C:/vcpkg/packages/opencl_x64-windows/', "$($env:RUNNER_TEMP.Replace('\','/'))/opencl/") | Set-Content -Path $f -Encoding UTF8 + } + + - name: Download OpenBLAS + id: get_openblas + if: ${{ matrix.build == 'openblas-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip" + curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE" + mkdir $env:RUNNER_TEMP/openblas + tar.exe -xvf $env:RUNNER_TEMP/openblas.zip -C $env:RUNNER_TEMP/openblas + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $lib = $(join-path $msvc 'bin\Hostx64\x64\lib.exe') + & $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll + + - name: Install Vulkan SDK + id: get_vulkan + if: ${{ matrix.build == 'kompute-x64' || matrix.build == 'vulkan-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/VulkanSDK-${env:VULKAN_VERSION}-Installer.exe" + & "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install + Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}" + Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin" + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. ${{ matrix.defines }} + cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS} + + - name: Add clblast.dll + id: add_clblast_dll + if: ${{ matrix.build == 'clblast' }} + run: | + git clone https://github.com/KhronosGroup/OpenCL-Headers + cd OpenCL-Headers + cmake -B build ` + -DBUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build --target install + git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader + cd OpenCL-ICD-Loader + cmake -B build-arm64-release ` + -A arm64 ` + -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build-arm64-release --target install --config release + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_2 + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Copy libcurl DLL + id: copy_curl_dll + run: | + cp $env:RUNNER_TEMP/curl/bin/libcurl-x64.dll ./build/bin/Release/libcurl-x64.dll + + - name: Add libopenblas.dll + id: add_libopenblas_dll + if: ${{ matrix.build == 'openblas-x64' }} + run: | + cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll + cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt + + - name: Check AVX512F support + id: check_avx512f + if: ${{ matrix.build == 'avx512-x64' }} + continue-on-error: true + run: | + cd build + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $cl = $(join-path $msvc 'bin\Hostx64\x64\cl.exe') + echo 'int main(void){unsigned int a[4];__cpuid(a,7);return !(a[1]&65536);}' >> avx512f.c + & $cl /O2 /GS- /kernel avx512f.c /link /nodefaultlib /entry:main + .\avx512f.exe && echo "AVX512F: YES" && ( echo HAS_AVX512F=1 >> $env:GITHUB_ENV ) || echo "AVX512F: NO" + + - name: Test + id: cmake_test + # not all machines have native AVX-512 + if: ${{ matrix.build != 'arm64' && matrix.build != 'clblast' && matrix.build != 'kompute' && matrix.build != 'vulkan' && (matrix.build != 'avx512' || steps.check_avx512f.outputs.has_avx512f == '1') }} + run: | + cd build + ctest -L main -C Release --verbose --timeout 900 + + - name: Test (Intel SDE) + if: ${{ matrix.build == 'avx512-x64' && (steps.check_avx512f.outputs.has_avx512f == '0') }} # use Intel SDE for AVX-512 emulation + if: ${{ matrix.build == 'avx512-x64' && env.HAS_AVX512F == '0' }} # use Intel SDE for AVX-512 emulation + run: | + curl.exe -o $env:RUNNER_TEMP/sde.tar.xz -L "https://downloadmirror.intel.com/813591/sde-external-${env:SDE_VERSION}-win.tar.xz" + # for some weird reason windows tar doesn't like sde tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar + $sde = $(join-path $env:RUNNER_TEMP sde-external-${env:SDE_VERSION}-win/sde.exe) + cd build + $env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1 + & $sde -future -- ctest -L main -C Release --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + Copy-Item LICENSE .\build\bin\Release\llama.cpp.txt + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip + name: llama-bin-win-${{ matrix.build }}-x64.zip + + windows-latest-cmake-cuda: + runs-on: windows-latest + + strategy: + matrix: + cuda: ['12.4', '11.7'] + build: ['cuda'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }}-${{ matrix.cuda }}-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Install Cuda Toolkit 11.7 + if: ${{ matrix.cuda == '11.7' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-11.7.4.6-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-11.7.101-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-11.7.91-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cudart-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvcc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvrtc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libcublas-windows-x86_64-11.7.4.6-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvtx-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\visual_studio_integration-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvprof-windows-x86_64-11.7.101-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cccl-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V11_7=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Cuda Toolkit 12.4 + if: ${{ matrix.cuda == '12.4' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-12.4.131-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-12.4.5.8-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-12.4.127-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cudart-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvcc-windows-x86_64-12.4.131-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvrtc-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libcublas-windows-x86_64-12.4.5.8-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvtx-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_profiler_api-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\visual_studio_integration-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvprof-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cccl-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V12_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Ninja + id: install_ninja + run: | + choco install ninja + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_3 + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\Release\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip + name: llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + - name: Copy and pack Cuda runtime + if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + run: | + echo "Cuda install location: ${{ env.CUDA_PATH }}" + $dst='.\build\bin\cudart\' + robocopy "${{env.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + robocopy "${{env.CUDA_PATH}}\lib" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + 7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip $dst\* + + - name: Upload Cuda runtime + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + name: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + windows-latest-cmake-sycl: + runs-on: windows-latest + + defaults: + run: + shell: bash + + env: + WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b380d914-366b-4b77-a74a-05e3c38b3514/intel-oneapi-base-toolkit-2025.0.0.882_offline.exe + WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel + ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI" + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-sycl + variant: sccache + evict-old-files: 1d + + - name: Install + run: | + scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL + + # TODO: add libcurl support ; we will also need to modify win-build-sycl.bat to accept user-specified args + + - name: Build + id: cmake_build + run: examples/sycl/win-build-sycl.bat + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Build the release package + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + echo "cp oneAPI running time dll files in ${{ env.ONEAPI_ROOT }} to ./build/bin" + + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_sycl_blas.5.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_core.2.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_tbb_thread.2.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_opencl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_loader.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_win_proxy_loader.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl8.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/svml_dispmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libmmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libiomp5md.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/dnnl/latest/bin/dnnl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/tbb/latest/bin/tbb12.dll" ./build/bin + + echo "cp oneAPI running time dll files to ./build/bin done" + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip ./build/bin/* + + - name: Upload the release package + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip + name: llama-bin-win-sycl-x64.zip + + windows-latest-cmake-hip: + if: ${{ github.event.inputs.create_release != 'true' }} + runs-on: windows-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }} + evict-old-files: 1d + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_4 + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DGGML_HIP=ON ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + + # TODO: reuse windows-latest-cmake-hip instead of duplicating this job + windows-latest-cmake-hip-release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + runs-on: windows-latest + + strategy: + matrix: + gpu_target: [gfx1100, gfx1101, gfx1030] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-hip-release + evict-old-files: 1d + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_5 + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DAMDGPU_TARGETS=${{ matrix.gpu_target }} ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_HIP=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + md "build\bin\rocblas\library\" + cp "${env:HIP_PATH}\bin\hipblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas\library\*" "build\bin\rocblas\library\" + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip .\build\bin\* + + - name: Upload artifacts + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + name: llama-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + + ios-xcode-build: + runs-on: macos-latest + + steps: + - name: Checkout code + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + - name: Build Xcode project + run: xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + zip --symlinks -r llama-${{ steps.tag.outputs.name }}-xcframework.zip build-apple/llama.xcframework + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-xcframework.zip + name: llama-${{ steps.tag.outputs.name }}-xcframework + + android-build: + runs-on: ubuntu-latest + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: android-build + evict-old-files: 1d + + - name: Set up JDK + uses: actions/setup-java@v3 + with: + java-version: 17 + distribution: zulu + + - name: Setup Android SDK + uses: android-actions/setup-android@v3 + with: + log-accepted-android-sdk-licenses: false + + - name: Build + run: | + cd examples/llama.android + + ./gradlew build --no-daemon + + release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + + runs-on: ubuntu-latest + + needs: + - ubuntu-cpu-cmake + - ubuntu-22-cmake-vulkan + - windows-latest-cmake + - windows-latest-cmake-cuda + - windows-latest-cmake-sycl + - windows-latest-cmake-hip-release + - macOS-latest-cmake-arm64 + - macOS-latest-cmake-x64 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: release + evict-old-files: 1d + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Download artifacts + id: download-artifact + uses: actions/download-artifact@v4 + with: + path: ./artifact + + - name: Move artifacts + id: move_artifacts + run: mkdir -p ./artifact/release && mv ./artifact/*/*.zip ./artifact/release + + - name: Create release + id: create_release + uses: ggml-org/action-create-release@v1 + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + with: + tag_name: ${{ steps.tag.outputs.name }} + + - name: Upload release + id: upload_release + uses: actions/github-script@v3 + with: + github-token: ${{secrets.GITHUB_TOKEN}} + script: | + const path = require('path'); + const fs = require('fs'); + const release_id = '${{ steps.create_release.outputs.id }}'; + for (let file of await fs.readdirSync('./artifact/release')) { + if (path.extname(file) === '.zip') { + console.log('uploadReleaseAsset', file); + await github.repos.uploadReleaseAsset({ + owner: context.repo.owner, + repo: context.repo.repo, + release_id: release_id, + name: file, + data: await fs.readFileSync(`./artifact/release/${file}`) + }); + } + } + +# ubuntu-latest-gcc: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-clang: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_COMPILER=clang +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-gcc-sanitized: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# sanitizer: [ADDRESS, THREAD, UNDEFINED] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=Debug -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON +# +# - name: Build +# run: | +# make +# +# windows: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# include: +# - arch: Win32 +# s2arc: x86 +# - arch: x64 +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Upload binaries +# uses: actions/upload-artifact@v4 +# with: +# name: llama-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# windows-blas: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# blas: [ON] +# include: +# - arch: Win32 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x86.zip +# s2arc: x86 +# - arch: x64 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x64.zip +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Fetch OpenBLAS +# if: matrix.blas == 'ON' +# run: | +# C:/msys64/usr/bin/wget.exe -qO blas.zip ${{ matrix.obzip }} +# 7z x blas.zip -oblas -y +# copy blas/include/cblas.h . +# copy blas/include/openblas_config.h . +# echo "blasdir=$env:GITHUB_WORKSPACE/blas" >> $env:GITHUB_ENV +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# -DLLAMA_SUPPORT_OPENBLAS=${{ matrix.blas }} +# -DCMAKE_LIBRARY_PATH="$env:blasdir/lib" +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Copy libopenblas.dll +# if: matrix.blas == 'ON' +# run: copy "$env:blasdir/bin/libopenblas.dll" build/bin/${{ matrix.build }} +# +# - name: Upload binaries +# if: matrix.blas == 'ON' +# uses: actions/upload-artifact@v4 +# with: +# name: llama-blas-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# emscripten: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# wget -q https://github.com/emscripten-core/emsdk/archive/master.tar.gz +# tar -xvf master.tar.gz +# emsdk-master/emsdk update +# emsdk-master/emsdk install latest +# emsdk-master/emsdk activate latest +# +# - name: Configure +# run: echo "tmp" +# +# - name: Build +# run: | +# pushd emsdk-master +# source ./emsdk_env.sh +# popd +# emcmake cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# make + + openEuler-latest-cmake-cann: + if: ${{ github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'Ascend NPU') }} + defaults: + run: + shell: bash -el {0} + runs-on: ubuntu-24.04-arm + strategy: + matrix: + cann: + - '8.1.RC1.alpha001-910b-openeuler22.03-py3.10' + device: + - 'ascend910b3' + build: + - 'Release' + container: ascendai/cann:${{ matrix.cann }} + steps: + - name: Checkout + uses: actions/checkout@v4 + + - name: Dependencies + run: | + yum update -y + yum install -y git gcc gcc-c++ make cmake libcurl-devel + + - name: Build + run: | + export LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/$(uname -m)-linux/devlib/:${LD_LIBRARY_PATH} + + cmake -S . -B build \ + -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ + -DGGML_CANN=on \ + -DSOC_TYPE=${{ matrix.device }} + cmake --build build -j $(nproc) diff --git a/.github/workflows/Untitled-5.txt b/.github/workflows/Untitled-5.txt new file mode 100644 index 0000000000000..9fa6cac3ba355 --- /dev/null +++ b/.github/workflows/Untitled-5.txt @@ -0,0 +1,1812 @@ +name: CI +description: | + This workflow builds and tests the llama.cpp project on various platforms. + It is triggered on push, pull request, or manually via workflow_dispatch. + It also creates a release when a new commit is pushed to the master branch or when manually triggered. + The workflow includes jobs for macOS, Linux, and Windows, with different configurations and dependencies. + The workflow uses concurrency to cancel in-progress jobs if a new commit is pushed to the same branch. + It uses ccache to speed up the build process by caching compiled files. + +on: + workflow_dispatch: # allows manual triggering + inputs: + create_release: + default: false + description: 'Create new release' + required: true + type: boolean + push: + branches: + - master + paths: ['.github/workflows/build.yml', '.github/workflows/build-linux-cross.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + pull_request: + types: [opened, synchronize, reopened] + paths: ['.github/workflows/build.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +# Fine-grant permission +# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token +permissions: + contents: write # for creating release + +env: + BRANCH_NAME: ${{ github.head_ref || github.ref_name }} + GGML_NLOOP: 3 + GGML_N_THREADS: 1 + LLAMA_LOG_COLORS: 1 + LLAMA_LOG_PREFIX: 1 + LLAMA_LOG_TIMESTAMPS: 1 + CREATE_RELEASE: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' }} + +jobs: + macOS-latest-cmake-arm64: + runs-on: macos-14 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-arm64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: "${{ github.event_name == 'workflow_dispatch' ? github.event.inputs.create_release == 'true' : github.ref == 'refs/heads/master' }}" + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip + name: llama-bin-macos-arm64.zip + + macOS-latest-cmake-x64: + runs-on: macos-13 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-x64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + # Metal is disabled due to intermittent failures with Github runners not having a GPU: + # https://github.com/ggml-org/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313 + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL=OFF \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip + name: llama-bin-macos-x64.zip + + ubuntu-cpu-cmake: + strategy: + matrix: + include: + - build: 'x64' + os: ubuntu-22.04 + - build: 'arm64' + os: ubuntu-22.04-arm + + runs-on: ${{ matrix.os }} + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-cpu-cmake + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Test llama2c conversion + id: llama2c_test + run: | + cd build + echo "Fetch tokenizer" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin + echo "Fetch llama2c model" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin + ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf + ./bin/llama-cli -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip + name: llama-bin-ubuntu-${{ matrix.build }}.zip + + ubuntu-latest-cmake-sanitizer: + runs-on: ubuntu-latest + + continue-on-error: true + + strategy: + matrix: + sanitizer: [ADDRESS, THREAD, UNDEFINED] + build_type: [Debug] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-sanitizer-${{ matrix.sanitizer }} + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + if: ${{ matrix.sanitizer != 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Build (no OpenMP) + id: cmake_build_no_openmp + if: ${{ matrix.sanitizer == 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \ + -DGGML_OPENMP=OFF + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-llguidance: + runs-on: ubuntu-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_LLGUIDANCE=ON + cmake --build . --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-cmake-rpc: + runs-on: ubuntu-latest + + continue-on-error: true + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-rpc + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose + + ubuntu-22-cmake-vulkan: + runs-on: ubuntu-22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-vulkan + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | sudo apt-key add - + sudo wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list + sudo apt-get update -y + sudo apt-get install -y build-essential mesa-vulkan-drivers vulkan-sdk libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_VULKAN=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + # This is using llvmpipe and runs slower than other backends + ctest -L main --verbose --timeout 2700 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip + name: llama-bin-ubuntu-vulkan-x64.zip + + ubuntu-22-cmake-hip: + runs-on: ubuntu-22.04 + container: rocm/dev-ubuntu-22.04:6.0.2 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-hip + evict-old-files: 1d + + - name: Build with native CMake HIP support + id: cmake_build + run: | + cmake -B build -S . \ + -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build --config Release -j $(nproc) + + - name: Build with legacy HIP support + id: cmake_build_legacy_hip + run: | + cmake -B build2 -S . \ + -DCMAKE_C_COMPILER=hipcc \ + -DCMAKE_CXX_COMPILER=hipcc \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build2 --config Release -j $(nproc) + + ubuntu-22-cmake-musa: + runs-on: ubuntu-22.04 + container: mthreads/musa:rc3.1.1-devel-ubuntu22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + apt-get update + apt-get install -y build-essential git cmake libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-musa + evict-old-files: 1d + + - name: Build with native CMake MUSA support + id: cmake_build + run: | + cmake -B build -S . \ + -DGGML_MUSA=ON + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl-fp16: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl-fp16 + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx \ + -DGGML_SYCL_F16=ON + cmake --build build --config Release -j $(nproc) + + build-linux-cross: + uses: ./.github/workflows/build-linux-cross.yml + + macOS-latest-cmake-ios: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-ios + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-tvos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-tvos + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=tvOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-visionos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=visionOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=1.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-swift: + runs-on: macos-latest + + strategy: + matrix: + destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-swift + evict-old-files: 1d + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build llama.cpp with CMake + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64" + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + windows-msys2: + runs-on: windows-latest + + strategy: + fail-fast: false + matrix: + include: + - { sys: UCRT64, env: ucrt-x86_64, build: Release } + - { sys: CLANG64, env: clang-x86_64, build: Release } + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-msys2 + variant: sccache + evict-old-files: 1d + + - name: Setup ${{ matrix.sys }} + uses: msys2/setup-msys2@v2 + with: + update: true + msystem: ${{matrix.sys}} + install: >- + base-devel + git + mingw-w64-${{matrix.env}}-toolchain + mingw-w64-${{matrix.env}}-cmake + mingw-w64-${{matrix.env}}-openblas + + - name: Setup for build + run: | + echo "Setting up build environment" + + - name: Build using CMake + shell: msys2 {0} + run: | + cmake -B build + cmake --build build --config ${{ matrix.build }} -j $(nproc) + + - name: Clean after building using CMake + shell: msys2 {0} + run: | + rm -rf build + + - name: Build using CMake w/ OpenBLAS + shell: msys2 {0} + run: | + cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS + cmake --build build --config ${{ matrix.build }} -j $(nproc) + # Removed duplicate environment key "CURL_PATH" from this job to avoid conflicts. + + windows-latest-cmake: + runs-on: windows-latest + + env: + OPENBLAS_VERSION: 0.3.23 + SDE_VERSION: 9.33.0-2024-01-07 + VULKAN_VERSION: 1.4.309.0 + + strategy: + matrix: + include: + - build: 'rpc' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_RPC=ON -DBUILD_SHARED_LIBS=ON' + - build: 'noavx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx2' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + - build: 'avx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx512' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON' + - build: 'clblast' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"' + - build: 'openblas' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"' + - build: 'kompute' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_KOMPUTE=ON -DKOMPUTE_OPT_DISABLE_VULKAN_VERSION_CHECK=ON -DBUILD_SHARED_LIBS=ON' + - build: 'vulkan' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_VULKAN=ON -DBUILD_SHARED_LIBS=ON' + - build: 'arm64' + defines: '-A ARM64 -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Clone Kompute submodule + id: clone_kompute + if: ${{ matrix.build == 'kompute-x64' }} + run: | + git submodule update --init kompute + + - name: Download OpenCL SDK + id: get_opencl + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/opencl.zip -L "https://github.com/KhronosGroup/OpenCL-SDK/releases/download/v${env:OPENCL_VERSION}/OpenCL-SDK-v${env:OPENCL_VERSION}-Win-x64.zip" + mkdir $env:RUNNER_TEMP/opencl + tar.exe -xvf $env:RUNNER_TEMP/opencl.zip --strip-components=1 -C $env:RUNNER_TEMP/opencl + + - name: Download CLBlast + id: get_clblast + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/clblast.7z -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-windows-x64.7z" + curl.exe -o $env:RUNNER_TEMP/CLBlast.LICENSE.txt -L "https://github.com/CNugteren/CLBlast/raw/${env:CLBLAST_VERSION}/LICENSE" + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/clblast.7z + rename-item $env:RUNNER_TEMP/CLBlast-${env:CLBLAST_VERSION}-windows-x64 clblast + foreach ($f in (gci -Recurse -Path "$env:RUNNER_TEMP/clblast" -Filter '*.cmake')) { + $txt = Get-Content -Path $f -Raw + $txt.Replace('C:/vcpkg/packages/opencl_x64-windows/', "$($env:RUNNER_TEMP.Replace('\','/'))/opencl/") | Set-Content -Path $f -Encoding UTF8 + } + + - name: Download OpenBLAS + id: get_openblas + if: ${{ matrix.build == 'openblas-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip" + curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE" + mkdir $env:RUNNER_TEMP/openblas + tar.exe -xvf $env:RUNNER_TEMP/openblas.zip -C $env:RUNNER_TEMP/openblas + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $lib = $(join-path $msvc 'bin\Hostx64\x64\lib.exe') + & $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll + + - name: Install Vulkan SDK + id: get_vulkan + if: ${{ matrix.build == 'kompute-x64' || matrix.build == 'vulkan-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/VulkanSDK-${env:VULKAN_VERSION}-Installer.exe" + & "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install + Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}" + Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin" + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. ${{ matrix.defines }} + cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS} + + - name: Add clblast.dll + id: add_clblast_dll + if: ${{ matrix.build == 'clblast' }} + run: | + git clone https://github.com/KhronosGroup/OpenCL-Headers + cd OpenCL-Headers + cmake -B build ` + -DBUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build --target install + git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader + cd OpenCL-ICD-Loader + cmake -B build-arm64-release ` + -A arm64 ` + -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build-arm64-release --target install --config release + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Copy libcurl DLL + id: copy_curl_dll + run: | + cp $env:RUNNER_TEMP/curl/bin/libcurl-x64.dll ./build/bin/Release/libcurl-x64.dll + + - name: Add libopenblas.dll + id: add_libopenblas_dll + if: ${{ matrix.build == 'openblas-x64' }} + run: | + cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll + cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt + + - name: Check AVX512F support + id: check_avx512f + if: ${{ matrix.build == 'avx512-x64' }} + continue-on-error: true + run: | + cd build + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $cl = $(join-path $msvc 'bin\Hostx64\x64\cl.exe') + echo 'int main(void){unsigned int a[4];__cpuid(a,7);return !(a[1]&65536);}' >> avx512f.c + & $cl /O2 /GS- /kernel avx512f.c /link /nodefaultlib /entry:main + .\avx512f.exe && echo "AVX512F: YES" && ( echo HAS_AVX512F=1 >> $env:GITHUB_ENV ) || echo "AVX512F: NO" + + - name: Test + id: cmake_test + # not all machines have native AVX-512 + if: ${{ matrix.build != 'arm64' && matrix.build != 'clblast' && matrix.build != 'kompute' && matrix.build != 'vulkan' && (matrix.build != 'avx512' || steps.check_avx512f.outputs.has_avx512f == '1') }} + run: | + cd build + ctest -L main -C Release --verbose --timeout 900 + + - name: Test (Intel SDE) + if: ${{ matrix.build == 'avx512-x64' && (steps.check_avx512f.outputs.has_avx512f == '0') }} # use Intel SDE for AVX-512 emulation + if: ${{ matrix.build == 'avx512-x64' && env.HAS_AVX512F == '0' }} # use Intel SDE for AVX-512 emulation + run: | + curl.exe -o $env:RUNNER_TEMP/sde.tar.xz -L "https://downloadmirror.intel.com/813591/sde-external-${env:SDE_VERSION}-win.tar.xz" + # for some weird reason windows tar doesn't like sde tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar + $sde = $(join-path $env:RUNNER_TEMP sde-external-${env:SDE_VERSION}-win/sde.exe) + cd build + $env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1 + & $sde -future -- ctest -L main -C Release --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + Copy-Item LICENSE .\build\bin\Release\llama.cpp.txt + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip + name: llama-bin-win-${{ matrix.build }}-x64.zip + + windows-latest-cmake-cuda: + runs-on: windows-latest + + strategy: + matrix: + cuda: ['12.4', '11.7'] + build: ['cuda'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }}-${{ matrix.cuda }}-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Install Cuda Toolkit 11.7 + if: ${{ matrix.cuda == '11.7' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-11.7.4.6-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-11.7.101-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-11.7.91-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cudart-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvcc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvrtc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libcublas-windows-x86_64-11.7.4.6-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvtx-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\visual_studio_integration-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvprof-windows-x86_64-11.7.101-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cccl-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V11_7=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Cuda Toolkit 12.4 + if: ${{ matrix.cuda == '12.4' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-12.4.131-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-12.4.5.8-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-12.4.127-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cudart-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvcc-windows-x86_64-12.4.131-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvrtc-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libcublas-windows-x86_64-12.4.5.8-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvtx-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_profiler_api-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\visual_studio_integration-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvprof-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cccl-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V12_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Ninja + id: install_ninja + run: | + choco install ninja + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\Release\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip + name: llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + - name: Copy and pack Cuda runtime + if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + run: | + echo "Cuda install location: ${{ env.CUDA_PATH }}" + $dst='.\build\bin\cudart\' + robocopy "${{env.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + robocopy "${{env.CUDA_PATH}}\lib" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + 7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip $dst\* + + - name: Upload Cuda runtime + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + name: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + windows-latest-cmake-sycl: + runs-on: windows-latest + + defaults: + run: + shell: bash + + env: + WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b380d914-366b-4b77-a74a-05e3c38b3514/intel-oneapi-base-toolkit-2025.0.0.882_offline.exe + WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel + ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI" + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-sycl + variant: sccache + evict-old-files: 1d + + - name: Install + run: | + scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL + + # TODO: add libcurl support ; we will also need to modify win-build-sycl.bat to accept user-specified args + + - name: Build + id: cmake_build + run: examples/sycl/win-build-sycl.bat + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Build the release package + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + echo "cp oneAPI running time dll files in ${{ env.ONEAPI_ROOT }} to ./build/bin" + + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_sycl_blas.5.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_core.2.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_tbb_thread.2.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_opencl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_loader.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_win_proxy_loader.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl8.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/svml_dispmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libmmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libiomp5md.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/dnnl/latest/bin/dnnl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/tbb/latest/bin/tbb12.dll" ./build/bin + + echo "cp oneAPI running time dll files to ./build/bin done" + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip ./build/bin/* + + - name: Upload the release package + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip + name: llama-bin-win-sycl-x64.zip + + windows-latest-cmake-hip: + if: ${{ github.event.inputs.create_release != 'true' }} + runs-on: windows-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }} + evict-old-files: 1d + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DGGML_HIP=ON ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + + # TODO: reuse windows-latest-cmake-hip instead of duplicating this job + windows-latest-cmake-hip-release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + runs-on: windows-latest + + strategy: + matrix: + gpu_target: [gfx1100, gfx1101, gfx1030] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-hip-release + evict-old-files: 1d + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DAMDGPU_TARGETS=${{ matrix.gpu_target }} ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_HIP=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + md "build\bin\rocblas\library\" + cp "${env:HIP_PATH}\bin\hipblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas\library\*" "build\bin\rocblas\library\" + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip .\build\bin\* + + - name: Upload artifacts + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + name: llama-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + + ios-xcode-build: + runs-on: macos-latest + + steps: + - name: Checkout code + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + - name: Build Xcode project + run: xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + zip --symlinks -r llama-${{ steps.tag.outputs.name }}-xcframework.zip build-apple/llama.xcframework + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-xcframework.zip + name: llama-${{ steps.tag.outputs.name }}-xcframework + + android-build: + runs-on: ubuntu-latest + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: android-build + evict-old-files: 1d + + - name: Set up JDK + uses: actions/setup-java@v3 + with: + java-version: 17 + distribution: zulu + + - name: Setup Android SDK + uses: android-actions/setup-android@v3 + with: + log-accepted-android-sdk-licenses: false + + - name: Build + run: | + cd examples/llama.android + + ./gradlew build --no-daemon + + release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + + runs-on: ubuntu-latest + + needs: + - ubuntu-cpu-cmake + - ubuntu-22-cmake-vulkan + - windows-latest-cmake + - windows-latest-cmake-cuda + - windows-latest-cmake-sycl + - windows-latest-cmake-hip-release + - macOS-latest-cmake-arm64 + - macOS-latest-cmake-x64 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: release + evict-old-files: 1d + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Download artifacts + id: download-artifact + uses: actions/download-artifact@v4 + with: + path: ./artifact + + - name: Move artifacts + id: move_artifacts + run: mkdir -p ./artifact/release && mv ./artifact/*/*.zip ./artifact/release + + - name: Create release + id: create_release + uses: ggml-org/action-create-release@v1 + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + with: + tag_name: ${{ steps.tag.outputs.name }} + + - name: Upload release + id: upload_release + uses: actions/github-script@v3 + with: + github-token: ${{secrets.GITHUB_TOKEN}} + script: | + const path = require('path'); + const fs = require('fs'); + const release_id = '${{ steps.create_release.outputs.id }}'; + for (let file of await fs.readdirSync('./artifact/release')) { + if (path.extname(file) === '.zip') { + console.log('uploadReleaseAsset', file); + await github.repos.uploadReleaseAsset({ + owner: context.repo.owner, + repo: context.repo.repo, + release_id: release_id, + name: file, + data: await fs.readFileSync(`./artifact/release/${file}`) + }); + } + } + +# ubuntu-latest-gcc: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-clang: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_COMPILER=clang +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-gcc-sanitized: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# sanitizer: [ADDRESS, THREAD, UNDEFINED] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=Debug -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON +# +# - name: Build +# run: | +# make +# +# windows: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# include: +# - arch: Win32 +# s2arc: x86 +# - arch: x64 +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Upload binaries +# uses: actions/upload-artifact@v4 +# with: +# name: llama-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# windows-blas: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# blas: [ON] +# include: +# - arch: Win32 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x86.zip +# s2arc: x86 +# - arch: x64 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x64.zip +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Fetch OpenBLAS +# if: matrix.blas == 'ON' +# run: | +# C:/msys64/usr/bin/wget.exe -qO blas.zip ${{ matrix.obzip }} +# 7z x blas.zip -oblas -y +# copy blas/include/cblas.h . +# copy blas/include/openblas_config.h . +# echo "blasdir=$env:GITHUB_WORKSPACE/blas" >> $env:GITHUB_ENV +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# -DLLAMA_SUPPORT_OPENBLAS=${{ matrix.blas }} +# -DCMAKE_LIBRARY_PATH="$env:blasdir/lib" +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Copy libopenblas.dll +# if: matrix.blas == 'ON' +# run: copy "$env:blasdir/bin/libopenblas.dll" build/bin/${{ matrix.build }} +# +# - name: Upload binaries +# if: matrix.blas == 'ON' +# uses: actions/upload-artifact@v4 +# with: +# name: llama-blas-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# emscripten: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# wget -q https://github.com/emscripten-core/emsdk/archive/master.tar.gz +# tar -xvf master.tar.gz +# emsdk-master/emsdk update +# emsdk-master/emsdk install latest +# emsdk-master/emsdk activate latest +# +# - name: Configure +# run: echo "tmp" +# +# - name: Build +# run: | +# pushd emsdk-master +# source ./emsdk_env.sh +# popd +# emcmake cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# make + + openEuler-latest-cmake-cann: + if: ${{ github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'Ascend NPU') }} + defaults: + run: + shell: bash -el {0} + runs-on: ubuntu-24.04-arm + strategy: + matrix: + cann: + - '8.1.RC1.alpha001-910b-openeuler22.03-py3.10' + device: + - 'ascend910b3' + build: + - 'Release' + container: ascendai/cann:${{ matrix.cann }} + steps: + - name: Checkout + uses: actions/checkout@v4 + + - name: Dependencies + run: | + yum update -y + yum install -y git gcc gcc-c++ make cmake libcurl-devel + + - name: Build + run: | + export LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/$(uname -m)-linux/devlib/:${LD_LIBRARY_PATH} + + cmake -S . -B build \ + -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ + -DGGML_CANN=on \ + -DSOC_TYPE=${{ matrix.device }} + cmake --build build -j $(nproc) diff --git a/.github/workflows/Untitled-6.txt b/.github/workflows/Untitled-6.txt new file mode 100644 index 0000000000000..9fa6cac3ba355 --- /dev/null +++ b/.github/workflows/Untitled-6.txt @@ -0,0 +1,1812 @@ +name: CI +description: | + This workflow builds and tests the llama.cpp project on various platforms. + It is triggered on push, pull request, or manually via workflow_dispatch. + It also creates a release when a new commit is pushed to the master branch or when manually triggered. + The workflow includes jobs for macOS, Linux, and Windows, with different configurations and dependencies. + The workflow uses concurrency to cancel in-progress jobs if a new commit is pushed to the same branch. + It uses ccache to speed up the build process by caching compiled files. + +on: + workflow_dispatch: # allows manual triggering + inputs: + create_release: + default: false + description: 'Create new release' + required: true + type: boolean + push: + branches: + - master + paths: ['.github/workflows/build.yml', '.github/workflows/build-linux-cross.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + pull_request: + types: [opened, synchronize, reopened] + paths: ['.github/workflows/build.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +# Fine-grant permission +# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token +permissions: + contents: write # for creating release + +env: + BRANCH_NAME: ${{ github.head_ref || github.ref_name }} + GGML_NLOOP: 3 + GGML_N_THREADS: 1 + LLAMA_LOG_COLORS: 1 + LLAMA_LOG_PREFIX: 1 + LLAMA_LOG_TIMESTAMPS: 1 + CREATE_RELEASE: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' }} + +jobs: + macOS-latest-cmake-arm64: + runs-on: macos-14 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-arm64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: "${{ github.event_name == 'workflow_dispatch' ? github.event.inputs.create_release == 'true' : github.ref == 'refs/heads/master' }}" + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip + name: llama-bin-macos-arm64.zip + + macOS-latest-cmake-x64: + runs-on: macos-13 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-x64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + # Metal is disabled due to intermittent failures with Github runners not having a GPU: + # https://github.com/ggml-org/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313 + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL=OFF \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip + name: llama-bin-macos-x64.zip + + ubuntu-cpu-cmake: + strategy: + matrix: + include: + - build: 'x64' + os: ubuntu-22.04 + - build: 'arm64' + os: ubuntu-22.04-arm + + runs-on: ${{ matrix.os }} + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-cpu-cmake + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Test llama2c conversion + id: llama2c_test + run: | + cd build + echo "Fetch tokenizer" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin + echo "Fetch llama2c model" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin + ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf + ./bin/llama-cli -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip + name: llama-bin-ubuntu-${{ matrix.build }}.zip + + ubuntu-latest-cmake-sanitizer: + runs-on: ubuntu-latest + + continue-on-error: true + + strategy: + matrix: + sanitizer: [ADDRESS, THREAD, UNDEFINED] + build_type: [Debug] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-sanitizer-${{ matrix.sanitizer }} + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + if: ${{ matrix.sanitizer != 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Build (no OpenMP) + id: cmake_build_no_openmp + if: ${{ matrix.sanitizer == 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \ + -DGGML_OPENMP=OFF + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-llguidance: + runs-on: ubuntu-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_LLGUIDANCE=ON + cmake --build . --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-cmake-rpc: + runs-on: ubuntu-latest + + continue-on-error: true + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-rpc + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose + + ubuntu-22-cmake-vulkan: + runs-on: ubuntu-22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-vulkan + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | sudo apt-key add - + sudo wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list + sudo apt-get update -y + sudo apt-get install -y build-essential mesa-vulkan-drivers vulkan-sdk libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_VULKAN=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + # This is using llvmpipe and runs slower than other backends + ctest -L main --verbose --timeout 2700 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip + name: llama-bin-ubuntu-vulkan-x64.zip + + ubuntu-22-cmake-hip: + runs-on: ubuntu-22.04 + container: rocm/dev-ubuntu-22.04:6.0.2 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-hip + evict-old-files: 1d + + - name: Build with native CMake HIP support + id: cmake_build + run: | + cmake -B build -S . \ + -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build --config Release -j $(nproc) + + - name: Build with legacy HIP support + id: cmake_build_legacy_hip + run: | + cmake -B build2 -S . \ + -DCMAKE_C_COMPILER=hipcc \ + -DCMAKE_CXX_COMPILER=hipcc \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build2 --config Release -j $(nproc) + + ubuntu-22-cmake-musa: + runs-on: ubuntu-22.04 + container: mthreads/musa:rc3.1.1-devel-ubuntu22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + apt-get update + apt-get install -y build-essential git cmake libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-musa + evict-old-files: 1d + + - name: Build with native CMake MUSA support + id: cmake_build + run: | + cmake -B build -S . \ + -DGGML_MUSA=ON + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl-fp16: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl-fp16 + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx \ + -DGGML_SYCL_F16=ON + cmake --build build --config Release -j $(nproc) + + build-linux-cross: + uses: ./.github/workflows/build-linux-cross.yml + + macOS-latest-cmake-ios: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-ios + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-tvos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-tvos + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=tvOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-visionos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=visionOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=1.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-swift: + runs-on: macos-latest + + strategy: + matrix: + destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-swift + evict-old-files: 1d + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build llama.cpp with CMake + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64" + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + windows-msys2: + runs-on: windows-latest + + strategy: + fail-fast: false + matrix: + include: + - { sys: UCRT64, env: ucrt-x86_64, build: Release } + - { sys: CLANG64, env: clang-x86_64, build: Release } + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-msys2 + variant: sccache + evict-old-files: 1d + + - name: Setup ${{ matrix.sys }} + uses: msys2/setup-msys2@v2 + with: + update: true + msystem: ${{matrix.sys}} + install: >- + base-devel + git + mingw-w64-${{matrix.env}}-toolchain + mingw-w64-${{matrix.env}}-cmake + mingw-w64-${{matrix.env}}-openblas + + - name: Setup for build + run: | + echo "Setting up build environment" + + - name: Build using CMake + shell: msys2 {0} + run: | + cmake -B build + cmake --build build --config ${{ matrix.build }} -j $(nproc) + + - name: Clean after building using CMake + shell: msys2 {0} + run: | + rm -rf build + + - name: Build using CMake w/ OpenBLAS + shell: msys2 {0} + run: | + cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS + cmake --build build --config ${{ matrix.build }} -j $(nproc) + # Removed duplicate environment key "CURL_PATH" from this job to avoid conflicts. + + windows-latest-cmake: + runs-on: windows-latest + + env: + OPENBLAS_VERSION: 0.3.23 + SDE_VERSION: 9.33.0-2024-01-07 + VULKAN_VERSION: 1.4.309.0 + + strategy: + matrix: + include: + - build: 'rpc' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_RPC=ON -DBUILD_SHARED_LIBS=ON' + - build: 'noavx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx2' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + - build: 'avx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx512' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON' + - build: 'clblast' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"' + - build: 'openblas' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"' + - build: 'kompute' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_KOMPUTE=ON -DKOMPUTE_OPT_DISABLE_VULKAN_VERSION_CHECK=ON -DBUILD_SHARED_LIBS=ON' + - build: 'vulkan' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_VULKAN=ON -DBUILD_SHARED_LIBS=ON' + - build: 'arm64' + defines: '-A ARM64 -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Clone Kompute submodule + id: clone_kompute + if: ${{ matrix.build == 'kompute-x64' }} + run: | + git submodule update --init kompute + + - name: Download OpenCL SDK + id: get_opencl + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/opencl.zip -L "https://github.com/KhronosGroup/OpenCL-SDK/releases/download/v${env:OPENCL_VERSION}/OpenCL-SDK-v${env:OPENCL_VERSION}-Win-x64.zip" + mkdir $env:RUNNER_TEMP/opencl + tar.exe -xvf $env:RUNNER_TEMP/opencl.zip --strip-components=1 -C $env:RUNNER_TEMP/opencl + + - name: Download CLBlast + id: get_clblast + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/clblast.7z -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-windows-x64.7z" + curl.exe -o $env:RUNNER_TEMP/CLBlast.LICENSE.txt -L "https://github.com/CNugteren/CLBlast/raw/${env:CLBLAST_VERSION}/LICENSE" + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/clblast.7z + rename-item $env:RUNNER_TEMP/CLBlast-${env:CLBLAST_VERSION}-windows-x64 clblast + foreach ($f in (gci -Recurse -Path "$env:RUNNER_TEMP/clblast" -Filter '*.cmake')) { + $txt = Get-Content -Path $f -Raw + $txt.Replace('C:/vcpkg/packages/opencl_x64-windows/', "$($env:RUNNER_TEMP.Replace('\','/'))/opencl/") | Set-Content -Path $f -Encoding UTF8 + } + + - name: Download OpenBLAS + id: get_openblas + if: ${{ matrix.build == 'openblas-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip" + curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE" + mkdir $env:RUNNER_TEMP/openblas + tar.exe -xvf $env:RUNNER_TEMP/openblas.zip -C $env:RUNNER_TEMP/openblas + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $lib = $(join-path $msvc 'bin\Hostx64\x64\lib.exe') + & $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll + + - name: Install Vulkan SDK + id: get_vulkan + if: ${{ matrix.build == 'kompute-x64' || matrix.build == 'vulkan-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/VulkanSDK-${env:VULKAN_VERSION}-Installer.exe" + & "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install + Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}" + Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin" + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. ${{ matrix.defines }} + cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS} + + - name: Add clblast.dll + id: add_clblast_dll + if: ${{ matrix.build == 'clblast' }} + run: | + git clone https://github.com/KhronosGroup/OpenCL-Headers + cd OpenCL-Headers + cmake -B build ` + -DBUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build --target install + git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader + cd OpenCL-ICD-Loader + cmake -B build-arm64-release ` + -A arm64 ` + -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build-arm64-release --target install --config release + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Copy libcurl DLL + id: copy_curl_dll + run: | + cp $env:RUNNER_TEMP/curl/bin/libcurl-x64.dll ./build/bin/Release/libcurl-x64.dll + + - name: Add libopenblas.dll + id: add_libopenblas_dll + if: ${{ matrix.build == 'openblas-x64' }} + run: | + cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll + cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt + + - name: Check AVX512F support + id: check_avx512f + if: ${{ matrix.build == 'avx512-x64' }} + continue-on-error: true + run: | + cd build + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $cl = $(join-path $msvc 'bin\Hostx64\x64\cl.exe') + echo 'int main(void){unsigned int a[4];__cpuid(a,7);return !(a[1]&65536);}' >> avx512f.c + & $cl /O2 /GS- /kernel avx512f.c /link /nodefaultlib /entry:main + .\avx512f.exe && echo "AVX512F: YES" && ( echo HAS_AVX512F=1 >> $env:GITHUB_ENV ) || echo "AVX512F: NO" + + - name: Test + id: cmake_test + # not all machines have native AVX-512 + if: ${{ matrix.build != 'arm64' && matrix.build != 'clblast' && matrix.build != 'kompute' && matrix.build != 'vulkan' && (matrix.build != 'avx512' || steps.check_avx512f.outputs.has_avx512f == '1') }} + run: | + cd build + ctest -L main -C Release --verbose --timeout 900 + + - name: Test (Intel SDE) + if: ${{ matrix.build == 'avx512-x64' && (steps.check_avx512f.outputs.has_avx512f == '0') }} # use Intel SDE for AVX-512 emulation + if: ${{ matrix.build == 'avx512-x64' && env.HAS_AVX512F == '0' }} # use Intel SDE for AVX-512 emulation + run: | + curl.exe -o $env:RUNNER_TEMP/sde.tar.xz -L "https://downloadmirror.intel.com/813591/sde-external-${env:SDE_VERSION}-win.tar.xz" + # for some weird reason windows tar doesn't like sde tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar + $sde = $(join-path $env:RUNNER_TEMP sde-external-${env:SDE_VERSION}-win/sde.exe) + cd build + $env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1 + & $sde -future -- ctest -L main -C Release --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + Copy-Item LICENSE .\build\bin\Release\llama.cpp.txt + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip + name: llama-bin-win-${{ matrix.build }}-x64.zip + + windows-latest-cmake-cuda: + runs-on: windows-latest + + strategy: + matrix: + cuda: ['12.4', '11.7'] + build: ['cuda'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }}-${{ matrix.cuda }}-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Install Cuda Toolkit 11.7 + if: ${{ matrix.cuda == '11.7' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-11.7.4.6-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-11.7.101-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-11.7.91-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cudart-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvcc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvrtc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libcublas-windows-x86_64-11.7.4.6-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvtx-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\visual_studio_integration-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvprof-windows-x86_64-11.7.101-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cccl-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V11_7=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Cuda Toolkit 12.4 + if: ${{ matrix.cuda == '12.4' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-12.4.131-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-12.4.5.8-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-12.4.127-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cudart-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvcc-windows-x86_64-12.4.131-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvrtc-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libcublas-windows-x86_64-12.4.5.8-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvtx-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_profiler_api-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\visual_studio_integration-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvprof-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cccl-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V12_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Ninja + id: install_ninja + run: | + choco install ninja + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\Release\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip + name: llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + - name: Copy and pack Cuda runtime + if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + run: | + echo "Cuda install location: ${{ env.CUDA_PATH }}" + $dst='.\build\bin\cudart\' + robocopy "${{env.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + robocopy "${{env.CUDA_PATH}}\lib" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + 7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip $dst\* + + - name: Upload Cuda runtime + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + name: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + windows-latest-cmake-sycl: + runs-on: windows-latest + + defaults: + run: + shell: bash + + env: + WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b380d914-366b-4b77-a74a-05e3c38b3514/intel-oneapi-base-toolkit-2025.0.0.882_offline.exe + WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel + ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI" + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-sycl + variant: sccache + evict-old-files: 1d + + - name: Install + run: | + scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL + + # TODO: add libcurl support ; we will also need to modify win-build-sycl.bat to accept user-specified args + + - name: Build + id: cmake_build + run: examples/sycl/win-build-sycl.bat + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Build the release package + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + echo "cp oneAPI running time dll files in ${{ env.ONEAPI_ROOT }} to ./build/bin" + + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_sycl_blas.5.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_core.2.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_tbb_thread.2.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_opencl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_loader.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_win_proxy_loader.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl8.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/svml_dispmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libmmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libiomp5md.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/dnnl/latest/bin/dnnl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/tbb/latest/bin/tbb12.dll" ./build/bin + + echo "cp oneAPI running time dll files to ./build/bin done" + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip ./build/bin/* + + - name: Upload the release package + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip + name: llama-bin-win-sycl-x64.zip + + windows-latest-cmake-hip: + if: ${{ github.event.inputs.create_release != 'true' }} + runs-on: windows-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }} + evict-old-files: 1d + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DGGML_HIP=ON ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + + # TODO: reuse windows-latest-cmake-hip instead of duplicating this job + windows-latest-cmake-hip-release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + runs-on: windows-latest + + strategy: + matrix: + gpu_target: [gfx1100, gfx1101, gfx1030] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-hip-release + evict-old-files: 1d + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DAMDGPU_TARGETS=${{ matrix.gpu_target }} ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_HIP=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + md "build\bin\rocblas\library\" + cp "${env:HIP_PATH}\bin\hipblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas\library\*" "build\bin\rocblas\library\" + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip .\build\bin\* + + - name: Upload artifacts + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + name: llama-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + + ios-xcode-build: + runs-on: macos-latest + + steps: + - name: Checkout code + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + - name: Build Xcode project + run: xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + zip --symlinks -r llama-${{ steps.tag.outputs.name }}-xcframework.zip build-apple/llama.xcframework + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-xcframework.zip + name: llama-${{ steps.tag.outputs.name }}-xcframework + + android-build: + runs-on: ubuntu-latest + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: android-build + evict-old-files: 1d + + - name: Set up JDK + uses: actions/setup-java@v3 + with: + java-version: 17 + distribution: zulu + + - name: Setup Android SDK + uses: android-actions/setup-android@v3 + with: + log-accepted-android-sdk-licenses: false + + - name: Build + run: | + cd examples/llama.android + + ./gradlew build --no-daemon + + release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + + runs-on: ubuntu-latest + + needs: + - ubuntu-cpu-cmake + - ubuntu-22-cmake-vulkan + - windows-latest-cmake + - windows-latest-cmake-cuda + - windows-latest-cmake-sycl + - windows-latest-cmake-hip-release + - macOS-latest-cmake-arm64 + - macOS-latest-cmake-x64 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: release + evict-old-files: 1d + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Download artifacts + id: download-artifact + uses: actions/download-artifact@v4 + with: + path: ./artifact + + - name: Move artifacts + id: move_artifacts + run: mkdir -p ./artifact/release && mv ./artifact/*/*.zip ./artifact/release + + - name: Create release + id: create_release + uses: ggml-org/action-create-release@v1 + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + with: + tag_name: ${{ steps.tag.outputs.name }} + + - name: Upload release + id: upload_release + uses: actions/github-script@v3 + with: + github-token: ${{secrets.GITHUB_TOKEN}} + script: | + const path = require('path'); + const fs = require('fs'); + const release_id = '${{ steps.create_release.outputs.id }}'; + for (let file of await fs.readdirSync('./artifact/release')) { + if (path.extname(file) === '.zip') { + console.log('uploadReleaseAsset', file); + await github.repos.uploadReleaseAsset({ + owner: context.repo.owner, + repo: context.repo.repo, + release_id: release_id, + name: file, + data: await fs.readFileSync(`./artifact/release/${file}`) + }); + } + } + +# ubuntu-latest-gcc: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-clang: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_COMPILER=clang +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-gcc-sanitized: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# sanitizer: [ADDRESS, THREAD, UNDEFINED] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=Debug -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON +# +# - name: Build +# run: | +# make +# +# windows: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# include: +# - arch: Win32 +# s2arc: x86 +# - arch: x64 +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Upload binaries +# uses: actions/upload-artifact@v4 +# with: +# name: llama-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# windows-blas: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# blas: [ON] +# include: +# - arch: Win32 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x86.zip +# s2arc: x86 +# - arch: x64 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x64.zip +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Fetch OpenBLAS +# if: matrix.blas == 'ON' +# run: | +# C:/msys64/usr/bin/wget.exe -qO blas.zip ${{ matrix.obzip }} +# 7z x blas.zip -oblas -y +# copy blas/include/cblas.h . +# copy blas/include/openblas_config.h . +# echo "blasdir=$env:GITHUB_WORKSPACE/blas" >> $env:GITHUB_ENV +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# -DLLAMA_SUPPORT_OPENBLAS=${{ matrix.blas }} +# -DCMAKE_LIBRARY_PATH="$env:blasdir/lib" +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Copy libopenblas.dll +# if: matrix.blas == 'ON' +# run: copy "$env:blasdir/bin/libopenblas.dll" build/bin/${{ matrix.build }} +# +# - name: Upload binaries +# if: matrix.blas == 'ON' +# uses: actions/upload-artifact@v4 +# with: +# name: llama-blas-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# emscripten: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# wget -q https://github.com/emscripten-core/emsdk/archive/master.tar.gz +# tar -xvf master.tar.gz +# emsdk-master/emsdk update +# emsdk-master/emsdk install latest +# emsdk-master/emsdk activate latest +# +# - name: Configure +# run: echo "tmp" +# +# - name: Build +# run: | +# pushd emsdk-master +# source ./emsdk_env.sh +# popd +# emcmake cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# make + + openEuler-latest-cmake-cann: + if: ${{ github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'Ascend NPU') }} + defaults: + run: + shell: bash -el {0} + runs-on: ubuntu-24.04-arm + strategy: + matrix: + cann: + - '8.1.RC1.alpha001-910b-openeuler22.03-py3.10' + device: + - 'ascend910b3' + build: + - 'Release' + container: ascendai/cann:${{ matrix.cann }} + steps: + - name: Checkout + uses: actions/checkout@v4 + + - name: Dependencies + run: | + yum update -y + yum install -y git gcc gcc-c++ make cmake libcurl-devel + + - name: Build + run: | + export LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/$(uname -m)-linux/devlib/:${LD_LIBRARY_PATH} + + cmake -S . -B build \ + -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ + -DGGML_CANN=on \ + -DSOC_TYPE=${{ matrix.device }} + cmake --build build -j $(nproc) diff --git a/.github/workflows/Untitled-7.txt b/.github/workflows/Untitled-7.txt new file mode 100644 index 0000000000000..6e67f30a1b109 --- /dev/null +++ b/.github/workflows/Untitled-7.txt @@ -0,0 +1,1812 @@ +name: CI +description: | + This workflow builds and tests the llama.cpp project on various platforms. + It is triggered on push, pull request, or manually via workflow_dispatch. + It also creates a release when a new commit is pushed to the master branch or when manually triggered. + The workflow includes jobs for macOS, Linux, and Windows, with different configurations and dependencies. + The workflow uses concurrency to cancel in-progress jobs if a new commit is pushed to the same branch. + It uses ccache to speed up the build process by caching compiled files. + +on: + workflow_dispatch: # allows manual triggering + inputs: + create_release: + default: false + description: 'Create new release' + required: true + type: boolean + push: + branches: + - master + paths: ['.github/workflows/build.yml', '.github/workflows/build-linux-cross.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + pull_request: + types: [opened, synchronize, reopened] + paths: ['.github/workflows/build.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +# Fine-grant permission +# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token +permissions: + contents: write # for creating release + +env: + BRANCH_NAME: ${{ github.head_ref || github.ref_name }} + GGML_NLOOP: 3 + GGML_N_THREADS: 1 + LLAMA_LOG_COLORS: 1 + LLAMA_LOG_PREFIX: 1 + LLAMA_LOG_TIMESTAMPS: 1 + CREATE_RELEASE: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' }} + +jobs: + macOS-latest-cmake-arm64: + runs-on: macos-14 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-arm64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: "${{ github.event_name == 'workflow_dispatch' ? github.event.inputs.create_release == 'true' : github.ref == 'refs/heads/master' }}" + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip + name: llama-bin-macos-arm64.zip + + macOS-latest-cmake-x64: + runs-on: macos-13 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-x64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + # Metal is disabled due to intermittent failures with Github runners not having a GPU: + # https://github.com/ggml-org/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313 + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL=OFF \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip + name: llama-bin-macos-x64.zip + + ubuntu-cpu-cmake: + strategy: + matrix: + include: + - build: 'x64' + os: ubuntu-22.04 + - build: 'arm64' + os: ubuntu-22.04-arm + + runs-on: ${{ matrix.os }} + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-cpu-cmake + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Test llama2c conversion + id: llama2c_test + run: | + cd build + echo "Fetch tokenizer" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin + echo "Fetch llama2c model" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin + ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf + ./bin/llama-cli -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip + name: llama-bin-ubuntu-${{ matrix.build }}.zip + + ubuntu-latest-cmake-sanitizer: + runs-on: ubuntu-latest + + continue-on-error: true + + strategy: + matrix: + sanitizer: [ADDRESS, THREAD, UNDEFINED] + build_type: [Debug] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-sanitizer-${{ matrix.sanitizer }} + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + if: ${{ matrix.sanitizer != 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Build (no OpenMP) + id: cmake_build_no_openmp + if: ${{ matrix.sanitizer == 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \ + -DGGML_OPENMP=OFF + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-llguidance: + runs-on: ubuntu-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_LLGUIDANCE=ON + cmake --build . --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-cmake-rpc: + runs-on: ubuntu-latest + + continue-on-error: true + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-rpc + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose + + ubuntu-22-cmake-vulkan: + runs-on: ubuntu-22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-vulkan + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | sudo apt-key add - + sudo wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list + sudo apt-get update -y + sudo apt-get install -y build-essential mesa-vulkan-drivers vulkan-sdk libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_VULKAN=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + # This is using llvmpipe and runs slower than other backends + ctest -L main --verbose --timeout 2700 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip + name: llama-bin-ubuntu-vulkan-x64.zip + + ubuntu-22-cmake-hip: + runs-on: ubuntu-22.04 + container: rocm/dev-ubuntu-22.04:6.0.2 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-hip + evict-old-files: 1d + + - name: Build with native CMake HIP support + id: cmake_build + run: | + cmake -B build -S . \ + -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build --config Release -j $(nproc) + + - name: Build with legacy HIP support + id: cmake_build_legacy_hip + run: | + cmake -B build2 -S . \ + -DCMAKE_C_COMPILER=hipcc \ + -DCMAKE_CXX_COMPILER=hipcc \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build2 --config Release -j $(nproc) + + ubuntu-22-cmake-musa: + runs-on: ubuntu-22.04 + container: mthreads/musa:rc3.1.1-devel-ubuntu22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + apt-get update + apt-get install -y build-essential git cmake libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-musa + evict-old-files: 1d + + - name: Build with native CMake MUSA support + id: cmake_build + run: | + cmake -B build -S . \ + -DGGML_MUSA=ON + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl-fp16: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl-fp16 + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx \ + -DGGML_SYCL_F16=ON + cmake --build build --config Release -j $(nproc) + + build-linux-cross: + uses: ./.github/workflows/build-linux-cross.yml + + macOS-latest-cmake-ios: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-ios + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-tvos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-tvos + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=tvOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-visionos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=visionOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=1.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-swift: + runs-on: macos-latest + + strategy: + matrix: + destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-swift + evict-old-files: 1d + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build llama.cpp with CMake + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64" + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + windows-msys2: + runs-on: windows-latest + + strategy: + fail-fast: false + matrix: + include: + - { sys: UCRT64, env: ucrt-x86_64, build: Release } + - { sys: CLANG64, env: clang-x86_64, build: Release } + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-msys2 + variant: sccache + evict-old-files: 1d + + - name: Setup ${{ matrix.sys }} + uses: msys2/setup-msys2@v2 + with: + update: true + msystem: ${{matrix.sys}} + install: >- + base-devel + git + mingw-w64-${{matrix.env}}-toolchain + mingw-w64-${{matrix.env}}-cmake + mingw-w64-${{matrix.env}}-openblas + + - name: Setup for build + run: | + echo "Setting up build environment" + + - name: Build using CMake + shell: msys2 {0} + run: | + cmake -B build + cmake --build build --config ${{ matrix.build }} -j $(nproc) + + - name: Clean after building using CMake + shell: msys2 {0} + run: | + rm -rf build + + - name: Build using CMake w/ OpenBLAS + shell: msys2 {0} + run: | + cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS + cmake --build build --config ${{ matrix.build }} -j $(nproc) + # Removed duplicate environment key "CURL_PATH" from this job to avoid conflicts. + + windows-latest-cmake: + runs-on: windows-latest + + env: + OPENBLAS_VERSION: 0.3.23 + SDE_VERSION: 9.33.0-2024-01-07 + VULKAN_VERSION: 1.4.309.0 + + strategy: + matrix: + include: + - build: 'rpc' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_RPC=ON -DBUILD_SHARED_LIBS=ON' + - build: 'noavx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx2' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + - build: 'avx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx512' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON' + - build: 'clblast' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"' + - build: 'openblas' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"' + - build: 'kompute' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_KOMPUTE=ON -DKOMPUTE_OPT_DISABLE_VULKAN_VERSION_CHECK=ON -DBUILD_SHARED_LIBS=ON' + - build: 'vulkan' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_VULKAN=ON -DBUILD_SHARED_LIBS=ON' + - build: 'arm64' + defines: '-A ARM64 -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Clone Kompute submodule + id: clone_kompute + if: ${{ matrix.build == 'kompute-x64' }} + run: | + git submodule update --init kompute + + - name: Download OpenCL SDK + id: get_opencl + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/opencl.zip -L "https://github.com/KhronosGroup/OpenCL-SDK/releases/download/v${env:OPENCL_VERSION}/OpenCL-SDK-v${env:OPENCL_VERSION}-Win-x64.zip" + mkdir $env:RUNNER_TEMP/opencl + tar.exe -xvf $env:RUNNER_TEMP/opencl.zip --strip-components=1 -C $env:RUNNER_TEMP/opencl + + - name: Download CLBlast + id: get_clblast + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/clblast.7z -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-windows-x64.7z" + curl.exe -o $env:RUNNER_TEMP/CLBlast.LICENSE.txt -L "https://github.com/CNugteren/CLBlast/raw/${env:CLBLAST_VERSION}/LICENSE" + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/clblast.7z + rename-item $env:RUNNER_TEMP/CLBlast-${env:CLBLAST_VERSION}-windows-x64 clblast + foreach ($f in (gci -Recurse -Path "$env:RUNNER_TEMP/clblast" -Filter '*.cmake')) { + $txt = Get-Content -Path $f -Raw + $txt.Replace('C:/vcpkg/packages/opencl_x64-windows/', "$($env:RUNNER_TEMP.Replace('\','/'))/opencl/") | Set-Content -Path $f -Encoding UTF8 + } + + - name: Download OpenBLAS + id: get_openblas + if: ${{ matrix.build == 'openblas-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip" + curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE" + mkdir $env:RUNNER_TEMP/openblas + tar.exe -xvf $env:RUNNER_TEMP/openblas.zip -C $env:RUNNER_TEMP/openblas + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $lib = $(join-path $msvc 'bin\Hostx64\x64\lib.exe') + & $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll + + - name: Install Vulkan SDK + id: get_vulkan + if: ${{ matrix.build == 'kompute-x64' || matrix.build == 'vulkan-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/VulkanSDK-${env:VULKAN_VERSION}-Installer.exe" + & "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install + Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}" + Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin" + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. ${{ matrix.defines }} + cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS} + + - name: Add clblast.dll + id: add_clblast_dll + if: ${{ matrix.build == 'clblast' }} + run: | + git clone https://github.com/KhronosGroup/OpenCL-Headers + cd OpenCL-Headers + cmake -B build ` + -DBUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build --target install + git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader + cd OpenCL-ICD-Loader + cmake -B build-arm64-release ` + -A arm64 ` + -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build-arm64-release --target install --config release + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_curl + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=OFF ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Copy libcurl DLL + id: copy_curl_dll + run: | + cp $env:RUNNER_TEMP/curl/bin/libcurl-x64.dll ./build/bin/Release/libcurl-x64.dll + + - name: Add libopenblas.dll + id: add_libopenblas_dll + if: ${{ matrix.build == 'openblas-x64' }} + run: | + cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll + cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt + + - name: Check AVX512F support + id: check_avx512f + if: ${{ matrix.build == 'avx512-x64' }} + continue-on-error: true + run: | + cd build + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $cl = $(join-path $msvc 'bin\Hostx64\x64\cl.exe') + echo 'int main(void){unsigned int a[4];__cpuid(a,7);return !(a[1]&65536);}' >> avx512f.c + & $cl /O2 /GS- /kernel avx512f.c /link /nodefaultlib /entry:main + .\avx512f.exe && echo "AVX512F: YES" && ( echo HAS_AVX512F=1 >> $env:GITHUB_ENV ) || echo "AVX512F: NO" + + - name: Test + id: cmake_test + # not all machines have native AVX-512 + if: ${{ matrix.build != 'arm64' && matrix.build != 'clblast' && matrix.build != 'kompute' && matrix.build != 'vulkan' && (matrix.build != 'avx512' || steps.check_avx512f.outputs.has_avx512f == '1') }} + run: | + cd build + ctest -L main -C Release --verbose --timeout 900 + + - name: Test (Intel SDE) + if: ${{ matrix.build == 'avx512-x64' && (steps.check_avx512f.outputs.has_avx512f == '0') }} # use Intel SDE for AVX-512 emulation + if: ${{ matrix.build == 'avx512-x64' && env.HAS_AVX512F == '0' }} # use Intel SDE for AVX-512 emulation + run: | + curl.exe -o $env:RUNNER_TEMP/sde.tar.xz -L "https://downloadmirror.intel.com/813591/sde-external-${env:SDE_VERSION}-win.tar.xz" + # for some weird reason windows tar doesn't like sde tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar + $sde = $(join-path $env:RUNNER_TEMP sde-external-${env:SDE_VERSION}-win/sde.exe) + cd build + $env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1 + & $sde -future -- ctest -L main -C Release --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + Copy-Item LICENSE .\build\bin\Release\llama.cpp.txt + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip + name: llama-bin-win-${{ matrix.build }}-x64.zip + + windows-latest-cmake-cuda: + runs-on: windows-latest + + strategy: + matrix: + cuda: ['12.4', '11.7'] + build: ['cuda'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }}-${{ matrix.cuda }}-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Install Cuda Toolkit 11.7 + if: ${{ matrix.cuda == '11.7' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-11.7.4.6-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-11.7.101-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-11.7.91-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cudart-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvcc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvrtc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libcublas-windows-x86_64-11.7.4.6-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvtx-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\visual_studio_integration-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvprof-windows-x86_64-11.7.101-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cccl-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V11_7=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Cuda Toolkit 12.4 + if: ${{ matrix.cuda == '12.4' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-12.4.131-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-12.4.5.8-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-12.4.127-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cudart-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvcc-windows-x86_64-12.4.131-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvrtc-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libcublas-windows-x86_64-12.4.5.8-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvtx-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_profiler_api-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\visual_studio_integration-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvprof-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cccl-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V12_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Ninja + id: install_ninja + run: | + choco install ninja + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_cuda + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON -DLLAMA_CUDA_FORCE_ARCH=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\Release\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip + name: llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + - name: Copy and pack Cuda runtime + if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + run: | + echo "Cuda install location: ${{ env.CUDA_PATH }}" + $dst='.\build\bin\cudart\' + robocopy "${{env.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + robocopy "${{env.CUDA_PATH}}\lib" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + 7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip $dst\* + + - name: Upload Cuda runtime + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + name: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + windows-latest-cmake-sycl: + runs-on: windows-latest + + defaults: + run: + shell: bash + + env: + WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b380d914-366b-4b77-a74a-05e3c38b3514/intel-oneapi-base-toolkit-2025.0.0.882_offline.exe + WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel + ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI" + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-sycl + variant: sccache + evict-old-files: 1d + + - name: Install + run: | + scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL + + # TODO: add libcurl support ; we will also need to modify win-build-sycl.bat to accept user-specified args + + - name: Build + id: cmake_build + run: examples/sycl/win-build-sycl.bat + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Build the release package + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + echo "cp oneAPI running time dll files in ${{ env.ONEAPI_ROOT }} to ./build/bin" + + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_sycl_blas.5.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_core.2.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_tbb_thread.2.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_opencl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_loader.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_win_proxy_loader.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl8.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/svml_dispmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libmmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libiomp5md.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/dnnl/latest/bin/dnnl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/tbb/latest/bin/tbb12.dll" ./build/bin + + echo "cp oneAPI running time dll files to ./build/bin done" + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip ./build/bin/* + + - name: Upload the release package + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip + name: llama-bin-win-sycl-x64.zip + + windows-latest-cmake-hip: + if: ${{ github.event.inputs.create_release != 'true' }} + runs-on: windows-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }} + evict-old-files: 1d + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_hip + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DGGML_HIP=ON ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + + # TODO: reuse windows-latest-cmake-hip instead of duplicating this job + windows-latest-cmake-hip-release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + runs-on: windows-latest + + strategy: + matrix: + gpu_target: [gfx1100, gfx1101, gfx1030] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-hip-release + evict-old-files: 1d + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_hip_release + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DAMDGPU_TARGETS=${{ matrix.gpu_target }} ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_HIP=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + md "build\bin\rocblas\library\" + cp "${env:HIP_PATH}\bin\hipblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas\library\*" "build\bin\rocblas\library\" + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip .\build\bin\* + + - name: Upload artifacts + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + name: llama-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + + ios-xcode-build: + runs-on: macos-latest + + steps: + - name: Checkout code + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + - name: Build Xcode project + run: xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + zip --symlinks -r llama-${{ steps.tag.outputs.name }}-xcframework.zip build-apple/llama.xcframework + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-xcframework.zip + name: llama-${{ steps.tag.outputs.name }}-xcframework + + android-build: + runs-on: ubuntu-latest + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: android-build + evict-old-files: 1d + + - name: Set up JDK + uses: actions/setup-java@v3 + with: + java-version: 17 + distribution: zulu + + - name: Setup Android SDK + uses: android-actions/setup-android@v3 + with: + log-accepted-android-sdk-licenses: false + + - name: Build + run: | + cd examples/llama.android + + ./gradlew build --no-daemon + + release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + + runs-on: ubuntu-latest + + needs: + - ubuntu-cpu-cmake + - ubuntu-22-cmake-vulkan + - windows-latest-cmake + - windows-latest-cmake-cuda + - windows-latest-cmake-sycl + - windows-latest-cmake-hip-release + - macOS-latest-cmake-arm64 + - macOS-latest-cmake-x64 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: release + evict-old-files: 1d + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Download artifacts + id: download-artifact + uses: actions/download-artifact@v4 + with: + path: ./artifact + + - name: Move artifacts + id: move_artifacts + run: mkdir -p ./artifact/release && mv ./artifact/*/*.zip ./artifact/release + + - name: Create release + id: create_release + uses: ggml-org/action-create-release@v1 + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + with: + tag_name: ${{ steps.tag.outputs.name }} + + - name: Upload release + id: upload_release + uses: actions/github-script@v3 + with: + github-token: ${{secrets.GITHUB_TOKEN}} + script: | + const path = require('path'); + const fs = require('fs'); + const release_id = '${{ steps.create_release.outputs.id }}'; + for (let file of await fs.readdirSync('./artifact/release')) { + if (path.extname(file) === '.zip') { + console.log('uploadReleaseAsset', file); + await github.repos.uploadReleaseAsset({ + owner: context.repo.owner, + repo: context.repo.repo, + release_id: release_id, + name: file, + data: await fs.readFileSync(`./artifact/release/${file}`) + }); + } + } + +# ubuntu-latest-gcc: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-clang: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_COMPILER=clang +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-gcc-sanitized: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# sanitizer: [ADDRESS, THREAD, UNDEFINED] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=Debug -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON +# +# - name: Build +# run: | +# make +# +# windows: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# include: +# - arch: Win32 +# s2arc: x86 +# - arch: x64 +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Upload binaries +# uses: actions/upload-artifact@v4 +# with: +# name: llama-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# windows-blas: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# blas: [ON] +# include: +# - arch: Win32 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x86.zip +# s2arc: x86 +# - arch: x64 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x64.zip +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Fetch OpenBLAS +# if: matrix.blas == 'ON' +# run: | +# C:/msys64/usr/bin/wget.exe -qO blas.zip ${{ matrix.obzip }} +# 7z x blas.zip -oblas -y +# copy blas/include/cblas.h . +# copy blas/include/openblas_config.h . +# echo "blasdir=$env:GITHUB_WORKSPACE/blas" >> $env:GITHUB_ENV +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# -DLLAMA_SUPPORT_OPENBLAS=${{ matrix.blas }} +# -DCMAKE_LIBRARY_PATH="$env:blasdir/lib" +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Copy libopenblas.dll +# if: matrix.blas == 'ON' +# run: copy "$env:blasdir/bin/libopenblas.dll" build/bin/${{ matrix.build }} +# +# - name: Upload binaries +# if: matrix.blas == 'ON' +# uses: actions/upload-artifact@v4 +# with: +# name: llama-blas-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# emscripten: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# wget -q https://github.com/emscripten-core/emsdk/archive/master.tar.gz +# tar -xvf master.tar.gz +# emsdk-master/emsdk update +# emsdk-master/emsdk install latest +# emsdk-master/emsdk activate latest +# +# - name: Configure +# run: echo "tmp" +# +# - name: Build +# run: | +# pushd emsdk-master +# source ./emsdk_env.sh +# popd +# emcmake cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# make + + openEuler-latest-cmake-cann: + if: ${{ github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'Ascend NPU') }} + defaults: + run: + shell: bash -el {0} + runs-on: ubuntu-24.04-arm + strategy: + matrix: + cann: + - '8.1.RC1.alpha001-910b-openeuler22.03-py3.10' + device: + - 'ascend910b3' + build: + - 'Release' + container: ascendai/cann:${{ matrix.cann }} + steps: + - name: Checkout + uses: actions/checkout@v4 + + - name: Dependencies + run: | + yum update -y + yum install -y git gcc gcc-c++ make cmake libcurl-devel + + - name: Build + run: | + export LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/$(uname -m)-linux/devlib/:${LD_LIBRARY_PATH} + + cmake -S . -B build \ + -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ + -DGGML_CANN=on \ + -DSOC_TYPE=${{ matrix.device }} + cmake --build build -j $(nproc) diff --git a/.github/workflows/Untitled-8.txt b/.github/workflows/Untitled-8.txt new file mode 100644 index 0000000000000..c8f36ffd49232 --- /dev/null +++ b/.github/workflows/Untitled-8.txt @@ -0,0 +1,1812 @@ +name: CI +description: | + This workflow builds and tests the llama.cpp project on various platforms. + It is triggered on push, pull request, or manually via workflow_dispatch. + It also creates a release when a new commit is pushed to the master branch or when manually triggered. + The workflow includes jobs for macOS, Linux, and Windows, with different configurations and dependencies. + The workflow uses concurrency to cancel in-progress jobs if a new commit is pushed to the same branch. + It uses ccache to speed up the build process by caching compiled files. + +on: + workflow_dispatch: # allows manual triggering + inputs: + create_release: + default: false + description: 'Create new release' + required: true + type: boolean + push: + branches: + - master + paths: ['.github/workflows/build.yml', '.github/workflows/build-linux-cross.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + pull_request: + types: [opened, synchronize, reopened] + paths: ['.github/workflows/build.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +# Fine-grant permission +# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token +permissions: + contents: write # for creating release + +env: + BRANCH_NAME: ${{ github.head_ref || github.ref_name }} + GGML_NLOOP: 3 + GGML_N_THREADS: 1 + LLAMA_LOG_COLORS: 1 + LLAMA_LOG_PREFIX: 1 + LLAMA_LOG_TIMESTAMPS: 1 + CREATE_RELEASE: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' }} + +jobs: + macOS-latest-cmake-arm64: + runs-on: macos-14 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-arm64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: "${{ github.event_name == 'workflow_dispatch' ? github.event.inputs.create_release == 'true' : github.ref == 'refs/heads/master' }}" + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip + name: llama-bin-macos-arm64.zip + + macOS-latest-cmake-x64: + runs-on: macos-13 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-x64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + # Metal is disabled due to intermittent failures with Github runners not having a GPU: + # https://github.com/ggml-org/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313 + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL=OFF \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip + name: llama-bin-macos-x64.zip + + ubuntu-cpu-cmake: + strategy: + matrix: + include: + - build: 'x64' + os: ubuntu-22.04 + - build: 'arm64' + os: ubuntu-22.04-arm + + runs-on: ${{ matrix.os }} + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-cpu-cmake + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Test llama2c conversion + id: llama2c_test + run: | + cd build + echo "Fetch tokenizer" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin + echo "Fetch llama2c model" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin + ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf + ./bin/llama-cli -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip + name: llama-bin-ubuntu-${{ matrix.build }}.zip + + ubuntu-latest-cmake-sanitizer: + runs-on: ubuntu-latest + + continue-on-error: true + + strategy: + matrix: + sanitizer: [ADDRESS, THREAD, UNDEFINED] + build_type: [Debug] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-sanitizer-${{ matrix.sanitizer }} + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + if: ${{ matrix.sanitizer != 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Build (no OpenMP) + id: cmake_build_no_openmp + if: ${{ matrix.sanitizer == 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \ + -DGGML_OPENMP=OFF + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-llguidance: + runs-on: ubuntu-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_LLGUIDANCE=ON + cmake --build . --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-cmake-rpc: + runs-on: ubuntu-latest + + continue-on-error: true + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-rpc + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose + + ubuntu-22-cmake-vulkan: + runs-on: ubuntu-22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-vulkan + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | sudo apt-key add - + sudo wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list + sudo apt-get update -y + sudo apt-get install -y build-essential mesa-vulkan-drivers vulkan-sdk libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_VULKAN=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + # This is using llvmpipe and runs slower than other backends + ctest -L main --verbose --timeout 2700 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip + name: llama-bin-ubuntu-vulkan-x64.zip + + ubuntu-22-cmake-hip: + runs-on: ubuntu-22.04 + container: rocm/dev-ubuntu-22.04:6.0.2 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-hip + evict-old-files: 1d + + - name: Build with native CMake HIP support + id: cmake_build + run: | + cmake -B build -S . \ + -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build --config Release -j $(nproc) + + - name: Build with legacy HIP support + id: cmake_build_legacy_hip + run: | + cmake -B build2 -S . \ + -DCMAKE_C_COMPILER=hipcc \ + -DCMAKE_CXX_COMPILER=hipcc \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build2 --config Release -j $(nproc) + + ubuntu-22-cmake-musa: + runs-on: ubuntu-22.04 + container: mthreads/musa:rc3.1.1-devel-ubuntu22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + apt-get update + apt-get install -y build-essential git cmake libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-musa + evict-old-files: 1d + + - name: Build with native CMake MUSA support + id: cmake_build + run: | + cmake -B build -S . \ + -DGGML_MUSA=ON + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl-fp16: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl-fp16 + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx \ + -DGGML_SYCL_F16=ON + cmake --build build --config Release -j $(nproc) + + build-linux-cross: + uses: ./.github/workflows/build-linux-cross.yml + + macOS-latest-cmake-ios: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-ios + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-tvos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-tvos + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=tvOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-visionos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=visionOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=1.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-swift: + runs-on: macos-latest + + strategy: + matrix: + destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-swift + evict-old-files: 1d + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build llama.cpp with CMake + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64" + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + windows-msys2: + runs-on: windows-latest + + strategy: + fail-fast: false + matrix: + include: + - { sys: UCRT64, env: ucrt-x86_64, build: Release } + - { sys: CLANG64, env: clang-x86_64, build: Release } + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-msys2 + variant: sccache + evict-old-files: 1d + + - name: Setup ${{ matrix.sys }} + uses: msys2/setup-msys2@v2 + with: + update: true + msystem: ${{matrix.sys}} + install: >- + base-devel + git + mingw-w64-${{matrix.env}}-toolchain + mingw-w64-${{matrix.env}}-cmake + mingw-w64-${{matrix.env}}-openblas + + - name: Setup for build + run: | + echo "Setting up build environment" + + - name: Build using CMake + shell: msys2 {0} + run: | + cmake -B build + cmake --build build --config ${{ matrix.build }} -j $(nproc) + + - name: Clean after building using CMake + shell: msys2 {0} + run: | + rm -rf build + + - name: Build using CMake w/ OpenBLAS + shell: msys2 {0} + run: | + cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS + cmake --build build --config ${{ matrix.build }} -j $(nproc) + # Removed duplicate environment key "CURL_PATH" from this job to avoid conflicts. + + windows-latest-cmake: + runs-on: windows-latest + + env: + OPENBLAS_VERSION: 0.3.23 + SDE_VERSION: 9.33.0-2024-01-07 + VULKAN_VERSION: 1.4.309.0 + + strategy: + matrix: + include: + - build: 'rpc' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_RPC=ON -DBUILD_SHARED_LIBS=ON' + - build: 'noavx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx2' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + - build: 'avx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx512' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON' + - build: 'clblast' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"' + - build: 'openblas' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"' + - build: 'kompute' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_KOMPUTE=ON -DKOMPUTE_OPT_DISABLE_VULKAN_VERSION_CHECK=ON -DBUILD_SHARED_LIBS=ON' + - build: 'vulkan' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_VULKAN=ON -DBUILD_SHARED_LIBS=ON' + - build: 'arm64' + defines: '-A ARM64 -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Clone Kompute submodule + id: clone_kompute + if: ${{ matrix.build == 'kompute-x64' }} + run: | + git submodule update --init kompute + + - name: Download OpenCL SDK + id: get_opencl + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/opencl.zip -L "https://github.com/KhronosGroup/OpenCL-SDK/releases/download/v${env:OPENCL_VERSION}/OpenCL-SDK-v${env:OPENCL_VERSION}-Win-x64.zip" + mkdir $env:RUNNER_TEMP/opencl + tar.exe -xvf $env:RUNNER_TEMP/opencl.zip --strip-components=1 -C $env:RUNNER_TEMP/opencl + + - name: Download CLBlast + id: get_clblast + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/clblast.7z -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-windows-x64.7z" + curl.exe -o $env:RUNNER_TEMP/CLBlast.LICENSE.txt -L "https://github.com/CNugteren/CLBlast/raw/${env:CLBLAST_VERSION}/LICENSE" + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/clblast.7z + rename-item $env:RUNNER_TEMP/CLBlast-${env:CLBLAST_VERSION}-windows-x64 clblast + foreach ($f in (gci -Recurse -Path "$env:RUNNER_TEMP/clblast" -Filter '*.cmake')) { + $txt = Get-Content -Path $f -Raw + $txt.Replace('C:/vcpkg/packages/opencl_x64-windows/', "$($env:RUNNER_TEMP.Replace('\','/'))/opencl/") | Set-Content -Path $f -Encoding UTF8 + } + + - name: Download OpenBLAS + id: get_openblas + if: ${{ matrix.build == 'openblas-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip" + curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE" + mkdir $env:RUNNER_TEMP/openblas + tar.exe -xvf $env:RUNNER_TEMP/openblas.zip -C $env:RUNNER_TEMP/openblas + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $lib = $(join-path $msvc 'bin\Hostx64\x64\lib.exe') + & $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll + + - name: Install Vulkan SDK + id: get_vulkan + if: ${{ matrix.build == 'kompute-x64' || matrix.build == 'vulkan-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/VulkanSDK-${env:VULKAN_VERSION}-Installer.exe" + & "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install + Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}" + Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin" + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. ${{ matrix.defines }} + cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS} + + - name: Add clblast.dll + id: add_clblast_dll + if: ${{ matrix.build == 'clblast' }} + run: | + git clone https://github.com/KhronosGroup/OpenCL-Headers + cd OpenCL-Headers + cmake -B build ` + -DBUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build --target install + git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader + cd OpenCL-ICD-Loader + cmake -B build-arm64-release ` + -A arm64 ` + -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build-arm64-release --target install --config release + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_curl + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=OFF ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Copy libcurl DLL + id: copy_curl_dll + run: | + cp $env:RUNNER_TEMP/curl/bin/libcurl-x64.dll ./build/bin/Release/libcurl-x64.dll + + - name: Add libopenblas.dll + id: add_libopenblas_dll + if: ${{ matrix.build == 'openblas-x64' }} + run: | + cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll + cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt + + - name: Check AVX512F support + id: check_avx512f + if: ${{ matrix.build == 'avx512-x64' }} + continue-on-error: true + run: | + cd build + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $cl = $(join-path $msvc 'bin\Hostx64\x64\cl.exe') + echo 'int main(void){unsigned int a[4];__cpuid(a,7);return !(a[1]&65536);}' >> avx512f.c + & $cl /O2 /GS- /kernel avx512f.c /link /nodefaultlib /entry:main + .\avx512f.exe && echo "AVX512F: YES" && ( echo HAS_AVX512F=1 >> $env:GITHUB_ENV ) || echo "AVX512F: NO" + + - name: Test + id: cmake_test + # not all machines have native AVX-512 + if: ${{ matrix.build != 'arm64' && matrix.build != 'clblast' && matrix.build != 'kompute' && matrix.build != 'vulkan' && (matrix.build != 'avx512' || steps.check_avx512f.outputs.has_avx512f == '1') }} + run: | + cd build + ctest -L main -C Release --verbose --timeout 900 + + - name: Test (Intel SDE) + if: ${{ matrix.build == 'avx512-x64' && (steps.check_avx512f.outputs.has_avx512f == '0') }} # use Intel SDE for AVX-512 emulation + if: ${{ matrix.build == 'avx512-x64' && env.HAS_AVX512F == '0' }} # use Intel SDE for AVX-512 emulation + run: | + curl.exe -o $env:RUNNER_TEMP/sde.tar.xz -L "https://downloadmirror.intel.com/813591/sde-external-${env:SDE_VERSION}-win.tar.xz" + # for some weird reason windows tar doesn't like sde tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar + $sde = $(join-path $env:RUNNER_TEMP sde-external-${env:SDE_VERSION}-win/sde.exe) + cd build + $env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1 + & $sde -future -- ctest -L main -C Release --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + Copy-Item LICENSE .\build\bin\Release\llama.cpp.txt + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip + name: llama-bin-win-${{ matrix.build }}-x64.zip + + windows-latest-cmake-cuda: + runs-on: windows-latest + + strategy: + matrix: + cuda: ['12.4', '11.7'] + build: ['cuda'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }}-${{ matrix.cuda }}-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Install Cuda Toolkit 11.7 + if: ${{ matrix.cuda == '11.7' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-11.7.4.6-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-11.7.101-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-11.7.91-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cudart-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvcc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvrtc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libcublas-windows-x86_64-11.7.4.6-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvtx-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\visual_studio_integration-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvprof-windows-x86_64-11.7.101-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cccl-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V11_7=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Cuda Toolkit 12.4 + if: ${{ matrix.cuda == '12.4' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-12.4.131-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-12.4.5.8-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-12.4.127-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cudart-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvcc-windows-x86_64-12.4.131-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvrtc-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libcublas-windows-x86_64-12.4.5.8-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvtx-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_profiler_api-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\visual_studio_integration-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvprof-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cccl-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V12_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Ninja + id: install_ninja + run: | + choco install ninja + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_cuda + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=all ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\Release\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip + name: llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + - name: Copy and pack Cuda runtime + if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + run: | + echo "Cuda install location: ${{ env.CUDA_PATH }}" + $dst='.\build\bin\cudart\' + robocopy "${{env.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + robocopy "${{env.CUDA_PATH}}\lib" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + 7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip $dst\* + + - name: Upload Cuda runtime + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + name: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + windows-latest-cmake-sycl: + runs-on: windows-latest + + defaults: + run: + shell: bash + + env: + WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b380d914-366b-4b77-a74a-05e3c38b3514/intel-oneapi-base-toolkit-2025.0.0.882_offline.exe + WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel + ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI" + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-sycl + variant: sccache + evict-old-files: 1d + + - name: Install + run: | + scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL + + # TODO: add libcurl support ; we will also need to modify win-build-sycl.bat to accept user-specified args + + - name: Build + id: cmake_build + run: examples/sycl/win-build-sycl.bat + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Build the release package + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + echo "cp oneAPI running time dll files in ${{ env.ONEAPI_ROOT }} to ./build/bin" + + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_sycl_blas.5.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_core.2.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_tbb_thread.2.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_opencl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_loader.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_win_proxy_loader.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl8.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/svml_dispmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libmmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libiomp5md.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/dnnl/latest/bin/dnnl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/tbb/latest/bin/tbb12.dll" ./build/bin + + echo "cp oneAPI running time dll files to ./build/bin done" + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip ./build/bin/* + + - name: Upload the release package + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip + name: llama-bin-win-sycl-x64.zip + + windows-latest-cmake-hip: + if: ${{ github.event.inputs.create_release != 'true' }} + runs-on: windows-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }} + evict-old-files: 1d + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_hip + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DGGML_HIP=ON ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + + # TODO: reuse windows-latest-cmake-hip instead of duplicating this job + windows-latest-cmake-hip-release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + runs-on: windows-latest + + strategy: + matrix: + gpu_target: [gfx1100, gfx1101, gfx1030] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-hip-release + evict-old-files: 1d + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build_hip_release + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DAMDGPU_TARGETS=${{ matrix.gpu_target }} ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_HIP=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + md "build\bin\rocblas\library\" + cp "${env:HIP_PATH}\bin\hipblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas\library\*" "build\bin\rocblas\library\" + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip .\build\bin\* + + - name: Upload artifacts + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + name: llama-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + + ios-xcode-build: + runs-on: macos-latest + + steps: + - name: Checkout code + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + - name: Build Xcode project + run: xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + run: | + zip --symlinks -r llama-${{ steps.tag.outputs.name }}-xcframework.zip build-apple/llama.xcframework + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-xcframework.zip + name: llama-${{ steps.tag.outputs.name }}-xcframework + + android-build: + runs-on: ubuntu-latest + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: android-build + evict-old-files: 1d + + - name: Set up JDK + uses: actions/setup-java@v3 + with: + java-version: 17 + distribution: zulu + + - name: Setup Android SDK + uses: android-actions/setup-android@v3 + with: + log-accepted-android-sdk-licenses: false + + - name: Build + run: | + cd examples/llama.android + + ./gradlew build --no-daemon + + release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + + runs-on: ubuntu-latest + + needs: + - ubuntu-cpu-cmake + - ubuntu-22-cmake-vulkan + - windows-latest-cmake + - windows-latest-cmake-cuda + - windows-latest-cmake-sycl + - windows-latest-cmake-hip-release + - macOS-latest-cmake-arm64 + - macOS-latest-cmake-x64 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: release + evict-old-files: 1d + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Download artifacts + id: download-artifact + uses: actions/download-artifact@v4 + with: + path: ./artifact + + - name: Move artifacts + id: move_artifacts + run: mkdir -p ./artifact/release && mv ./artifact/*/*.zip ./artifact/release + + - name: Create release + id: create_release + uses: ggml-org/action-create-release@v1 + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + with: + tag_name: ${{ steps.tag.outputs.name }} + + - name: Upload release + id: upload_release + uses: actions/github-script@v3 + with: + github-token: ${{secrets.GITHUB_TOKEN}} + script: | + const path = require('path'); + const fs = require('fs'); + const release_id = '${{ steps.create_release.outputs.id }}'; + for (let file of await fs.readdirSync('./artifact/release')) { + if (path.extname(file) === '.zip') { + console.log('uploadReleaseAsset', file); + await github.repos.uploadReleaseAsset({ + owner: context.repo.owner, + repo: context.repo.repo, + release_id: release_id, + name: file, + data: await fs.readFileSync(`./artifact/release/${file}`) + }); + } + } + +# ubuntu-latest-gcc: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-clang: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_COMPILER=clang +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-gcc-sanitized: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# sanitizer: [ADDRESS, THREAD, UNDEFINED] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=Debug -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON +# +# - name: Build +# run: | +# make +# +# windows: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# include: +# - arch: Win32 +# s2arc: x86 +# - arch: x64 +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Upload binaries +# uses: actions/upload-artifact@v4 +# with: +# name: llama-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# windows-blas: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# blas: [ON] +# include: +# - arch: Win32 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x86.zip +# s2arc: x86 +# - arch: x64 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x64.zip +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Fetch OpenBLAS +# if: matrix.blas == 'ON' +# run: | +# C:/msys64/usr/bin/wget.exe -qO blas.zip ${{ matrix.obzip }} +# 7z x blas.zip -oblas -y +# copy blas/include/cblas.h . +# copy blas/include/openblas_config.h . +# echo "blasdir=$env:GITHUB_WORKSPACE/blas" >> $env:GITHUB_ENV +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# -DLLAMA_SUPPORT_OPENBLAS=${{ matrix.blas }} +# -DCMAKE_LIBRARY_PATH="$env:blasdir/lib" +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Copy libopenblas.dll +# if: matrix.blas == 'ON' +# run: copy "$env:blasdir/bin/libopenblas.dll" build/bin/${{ matrix.build }} +# +# - name: Upload binaries +# if: matrix.blas == 'ON' +# uses: actions/upload-artifact@v4 +# with: +# name: llama-blas-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# emscripten: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# wget -q https://github.com/emscripten-core/emsdk/archive/master.tar.gz +# tar -xvf master.tar.gz +# emsdk-master/emsdk update +# emsdk-master/emsdk install latest +# emsdk-master/emsdk activate latest +# +# - name: Configure +# run: echo "tmp" +# +# - name: Build +# run: | +# pushd emsdk-master +# source ./emsdk_env.sh +# popd +# emcmake cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# make + + openEuler-latest-cmake-cann: + if: ${{ github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'Ascend NPU') }} + defaults: + run: + shell: bash -el {0} + runs-on: ubuntu-24.04-arm + strategy: + matrix: + cann: + - '8.1.RC1.alpha001-910b-openeuler22.03-py3.10' + device: + - 'ascend910b3' + build: + - 'Release' + container: ascendai/cann:${{ matrix.cann }} + steps: + - name: Checkout + uses: actions/checkout@v4 + + - name: Dependencies + run: | + yum update -y + yum install -y git gcc gcc-c++ make cmake libcurl-devel + + - name: Build + run: | + export LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/$(uname -m)-linux/devlib/:${LD_LIBRARY_PATH} + + cmake -S . -B build \ + -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ + -DGGML_CANN=on \ + -DSOC_TYPE=${{ matrix.device }} + cmake --build build -j $(nproc) diff --git a/.github/workflows/Untitled-9.txt b/.github/workflows/Untitled-9.txt new file mode 100644 index 0000000000000..e31e431ce9649 --- /dev/null +++ b/.github/workflows/Untitled-9.txt @@ -0,0 +1,1811 @@ +name: CI +description: | + This workflow builds and tests the llama.cpp project on various platforms. + It is triggered on push, pull request, or manually via workflow_dispatch. + It also creates a release when a new commit is pushed to the master branch or when manually triggered. + The workflow includes jobs for macOS, Linux, and Windows, with different configurations and dependencies. + The workflow uses concurrency to cancel in-progress jobs if a new commit is pushed to the same branch. + It uses ccache to speed up the build process by caching compiled files. + +on: + workflow_dispatch: # allows manual triggering + inputs: + create_release: + default: false + description: 'Create new release' + required: true + type: boolean + push: + branches: + - master + paths: ['.github/workflows/build.yml', '.github/workflows/build-linux-cross.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + pull_request: + types: [opened, synchronize, reopened] + paths: ['.github/workflows/build.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +# Fine-grant permission +# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token +permissions: + contents: write # for creating release + +env: + BRANCH_NAME: ${{ github.head_ref || github.ref_name }} + GGML_NLOOP: 3 + GGML_N_THREADS: 1 + LLAMA_LOG_COLORS: 1 + LLAMA_LOG_PREFIX: 1 + LLAMA_LOG_TIMESTAMPS: 1 + CREATE_RELEASE: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' }} + +jobs: + macOS-latest-cmake-arm64: + runs-on: macos-14 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-arm64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: "${{ github.event_name == 'workflow_dispatch' ? github.event.inputs.create_release == 'true' : github.ref == 'refs/heads/master' }}" + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip + name: llama-bin-macos-arm64.zip + + macOS-latest-cmake-x64: + runs-on: macos-13 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-x64 + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + brew install curl + + - name: Build + id: cmake_build + run: | + sysctl -a + # Metal is disabled due to intermittent failures with Github runners not having a GPU: + # https://github.com/ggml-org/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313 + cmake -B build \ + -DCMAKE_BUILD_RPATH="@loader_path" \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_METAL=OFF \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ (github.event_name == 'push' && github.ref == 'refs/heads/master') || (github.event.inputs.create_release == 'true') }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip + name: llama-bin-macos-x64.zip + + ubuntu-cpu-cmake: + strategy: + matrix: + include: + - build: 'x64' + os: ubuntu-22.04 + - build: 'arm64' + os: ubuntu-22.04-arm + + runs-on: ${{ matrix.os }} + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-cpu-cmake + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L 'main|curl' --verbose --timeout 900 + + - name: Test llama2c conversion + id: llama2c_test + run: | + cd build + echo "Fetch tokenizer" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin + echo "Fetch llama2c model" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin + ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf + ./bin/llama-cli -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ (github.event_name == 'push' && github.ref == 'refs/heads/master') || (github.event.inputs.create_release == 'true') }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip + name: llama-bin-ubuntu-${{ matrix.build }}.zip + + ubuntu-latest-cmake-sanitizer: + runs-on: ubuntu-latest + + continue-on-error: true + + strategy: + matrix: + sanitizer: [ADDRESS, THREAD, UNDEFINED] + build_type: [Debug] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-sanitizer-${{ matrix.sanitizer }} + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + if: ${{ matrix.sanitizer != 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Build (no OpenMP) + id: cmake_build_no_openmp + if: ${{ matrix.sanitizer == 'THREAD' }} + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \ + -DGGML_OPENMP=OFF + cmake --build build --config ${{ matrix.build_type }} -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-llguidance: + runs-on: ubuntu-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DLLAMA_LLGUIDANCE=ON + cmake --build . --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-latest-cmake-rpc: + runs-on: ubuntu-latest + + continue-on-error: true + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-latest-cmake-rpc + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_RPC=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose + + ubuntu-22-cmake-vulkan: + runs-on: ubuntu-22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-vulkan + evict-old-files: 1d + + - name: Dependencies + id: depends + run: | + wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | sudo apt-key add - + sudo wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list + sudo apt-get update -y + sudo apt-get install -y build-essential mesa-vulkan-drivers vulkan-sdk libcurl4-openssl-dev + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DGGML_VULKAN=ON + cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + # This is using llvmpipe and runs slower than other backends + ctest -L main --verbose --timeout 2700 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ (github.event_name == 'push' && github.ref == 'refs/heads/master') || (github.event.inputs.create_release == 'true') }} + run: | + cp LICENSE ./build/bin/ + zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip ./build/bin/* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip + name: llama-bin-ubuntu-vulkan-x64.zip + + ubuntu-22-cmake-hip: + runs-on: ubuntu-22.04 + container: rocm/dev-ubuntu-22.04:6.0.2 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-hip + evict-old-files: 1d + + - name: Build with native CMake HIP support + id: cmake_build + run: | + cmake -B build -S . \ + -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build --config Release -j $(nproc) + + - name: Build with legacy HIP support + id: cmake_build_legacy_hip + run: | + cmake -B build2 -S . \ + -DCMAKE_C_COMPILER=hipcc \ + -DCMAKE_CXX_COMPILER=hipcc \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGGML_HIP=ON + cmake --build build2 --config Release -j $(nproc) + + ubuntu-22-cmake-musa: + runs-on: ubuntu-22.04 + container: mthreads/musa:rc3.1.1-devel-ubuntu22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + apt-get update + apt-get install -y build-essential git cmake libcurl4-openssl-dev + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-musa + evict-old-files: 1d + + - name: Build with native CMake MUSA support + id: cmake_build + run: | + cmake -B build -S . \ + -DGGML_MUSA=ON + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx + cmake --build build --config Release -j $(nproc) + + ubuntu-22-cmake-sycl-fp16: + runs-on: ubuntu-22.04 + + continue-on-error: true + + steps: + - uses: actions/checkout@v4 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp libcurl4-openssl-dev + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ubuntu-22-cmake-sycl-fp16 + evict-old-files: 1d + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + cmake -B build \ + -DGGML_SYCL=ON \ + -DCMAKE_C_COMPILER=icx \ + -DCMAKE_CXX_COMPILER=icpx \ + -DGGML_SYCL_F16=ON + cmake --build build --config Release -j $(nproc) + + build-linux-cross: + uses: ./.github/workflows/build-linux-cross.yml + + macOS-latest-cmake-ios: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-ios + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-tvos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-cmake-tvos + evict-old-files: 1d + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=tvOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-cmake-visionos: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_BUILD_COMMON=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=visionOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=1.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + macOS-latest-swift: + runs-on: macos-latest + + strategy: + matrix: + destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: macOS-latest-swift + evict-old-files: 1d + - name: Dependencies + id: depends + continue-on-error: true + run: | + brew update + + - name: Build llama.cpp with CMake + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64" + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + windows-msys2: + runs-on: windows-latest + + strategy: + fail-fast: false + matrix: + include: + - { sys: UCRT64, env: ucrt-x86_64, build: Release } + - { sys: CLANG64, env: clang-x86_64, build: Release } + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-msys2 + variant: sccache + evict-old-files: 1d + + - name: Setup ${{ matrix.sys }} + uses: msys2/setup-msys2@v2 + with: + update: true + msystem: ${{matrix.sys}} + install: >- + base-devel + git + mingw-w64-${{matrix.env}}-toolchain + mingw-w64-${{matrix.env}}-cmake + mingw-w64-${{matrix.env}}-openblas + + - name: Setup for build + run: | + echo "Setting up build environment" + + - name: Build using CMake + shell: msys2 {0} + run: | + cmake -B build + cmake --build build --config ${{ matrix.build }} -j $(nproc) + + - name: Clean after building using CMake + shell: msys2 {0} + run: | + rm -rf build + + - name: Build using CMake w/ OpenBLAS + shell: msys2 {0} + run: | + cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS + cmake --build build --config ${{ matrix.build }} -j $(nproc) + # Removed duplicate environment key "CURL_PATH" from this job to avoid conflicts. + + windows-latest-cmake: + runs-on: windows-latest + + env: + OPENBLAS_VERSION: 0.3.23 + SDE_VERSION: 9.33.0-2024-01-07 + VULKAN_VERSION: 1.4.309.0 + + strategy: + matrix: + include: + - build: 'rpc' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_RPC=ON -DBUILD_SHARED_LIBS=ON' + - build: 'noavx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx2' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + - build: 'avx' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SHARED_LIBS=ON' + - build: 'avx512' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON' + - build: 'clblast' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"' + - build: 'openblas' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"' + - build: 'kompute' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_KOMPUTE=ON -DKOMPUTE_OPT_DISABLE_VULKAN_VERSION_CHECK=ON -DBUILD_SHARED_LIBS=ON' + - build: 'vulkan' + defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_VULKAN=ON -DBUILD_SHARED_LIBS=ON' + - build: 'arm64' + defines: '-A ARM64 -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON' + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Clone Kompute submodule + id: clone_kompute + if: ${{ matrix.build == 'kompute-x64' }} + run: | + git submodule update --init kompute + + - name: Download OpenCL SDK + id: get_opencl + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/opencl.zip -L "https://github.com/KhronosGroup/OpenCL-SDK/releases/download/v${env:OPENCL_VERSION}/OpenCL-SDK-v${env:OPENCL_VERSION}-Win-x64.zip" + mkdir $env:RUNNER_TEMP/opencl + tar.exe -xvf $env:RUNNER_TEMP/opencl.zip --strip-components=1 -C $env:RUNNER_TEMP/opencl + + - name: Download CLBlast + id: get_clblast + if: ${{ matrix.build == 'clblast' }} + run: | + curl.exe -o $env:RUNNER_TEMP/clblast.7z -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-windows-x64.7z" + curl.exe -o $env:RUNNER_TEMP/CLBlast.LICENSE.txt -L "https://github.com/CNugteren/CLBlast/raw/${env:CLBLAST_VERSION}/LICENSE" + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/clblast.7z + rename-item $env:RUNNER_TEMP/CLBlast-${env:CLBLAST_VERSION}-windows-x64 clblast + foreach ($f in (gci -Recurse -Path "$env:RUNNER_TEMP/clblast" -Filter '*.cmake')) { + $txt = Get-Content -Path $f -Raw + $txt.Replace('C:/vcpkg/packages/opencl_x64-windows/', "$($env:RUNNER_TEMP.Replace('\','/'))/opencl/") | Set-Content -Path $f -Encoding UTF8 + } + + - name: Download OpenBLAS + id: get_openblas + if: ${{ matrix.build == 'openblas-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip" + curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE" + mkdir $env:RUNNER_TEMP/openblas + tar.exe -xvf $env:RUNNER_TEMP/openblas.zip -C $env:RUNNER_TEMP/openblas + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $lib = $(join-path $msvc 'bin\Hostx64\x64\lib.exe') + & $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll + + - name: Install Vulkan SDK + id: get_vulkan + if: ${{ matrix.build == 'kompute-x64' || matrix.build == 'vulkan-x64' }} + run: | + curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/VulkanSDK-${env:VULKAN_VERSION}-Installer.exe" + & "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install + Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}" + Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin" + + - name: Build + id: cmake_build + run: | + mkdir build + cd build + cmake .. ${{ matrix.defines }} + cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS} + + - name: Add clblast.dll + id: add_clblast_dll + if: ${{ matrix.build == 'clblast' }} + run: | + git clone https://github.com/KhronosGroup/OpenCL-Headers + cd OpenCL-Headers + cmake -B build ` + -DBUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build --target install + git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader + cd OpenCL-ICD-Loader + cmake -B build-arm64-release ` + -A arm64 ` + -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build-arm64-release --target install --config release + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Copy libcurl DLL + id: copy_curl_dll + run: | + cp $env:RUNNER_TEMP/curl/bin/libcurl-x64.dll ./build/bin/Release/libcurl-x64.dll + + - name: Add libopenblas.dll + id: add_libopenblas_dll + if: ${{ matrix.build == 'openblas-x64' }} + run: | + cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll + cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt + + - name: Check AVX512F support + id: check_avx512f + if: ${{ matrix.build == 'avx512-x64' }} + continue-on-error: true + run: | + cd build + $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) + $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) + $cl = $(join-path $msvc 'bin\Hostx64\x64\cl.exe') + echo 'int main(void){unsigned int a[4];__cpuid(a,7);return !(a[1]&65536);}' >> avx512f.c + & $cl /O2 /GS- /kernel avx512f.c /link /nodefaultlib /entry:main + .\avx512f.exe && echo "AVX512F: YES" && ( echo HAS_AVX512F=1 >> $env:GITHUB_ENV ) || echo "AVX512F: NO" + + - name: Test + id: cmake_test + # not all machines have native AVX-512 + if: ${{ matrix.build != 'arm64' && matrix.build != 'clblast' && matrix.build != 'kompute' && matrix.build != 'vulkan' && (matrix.build != 'avx512' || steps.check_avx512f.outputs.has_avx512f == '1') }} + run: | + cd build + ctest -L main -C Release --verbose --timeout 900 + + - name: Test (Intel SDE) + if: ${{ matrix.build == 'avx512-x64' && (steps.check_avx512f.outputs.has_avx512f == '0' || env.HAS_AVX512F == '0') }} # use Intel SDE for AVX-512 emulation + run: | + curl.exe -o $env:RUNNER_TEMP/sde.tar.xz -L "https://downloadmirror.intel.com/813591/sde-external-${env:SDE_VERSION}-win.tar.xz" + # for some weird reason windows tar doesn't like sde tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar.xz + 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar + $sde = $(join-path $env:RUNNER_TEMP sde-external-${env:SDE_VERSION}-win/sde.exe) + cd build + $env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1 + & $sde -future -- ctest -L main -C Release --verbose --timeout 900 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ (github.event_name == 'push' && github.ref == 'refs/heads/master') || (github.event.inputs.create_release == 'true') }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + Copy-Item LICENSE .\build\bin\Release\llama.cpp.txt + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip + name: llama-bin-win-${{ matrix.build }}-x64.zip + + windows-latest-cmake-cuda: + runs-on: windows-latest + + strategy: + matrix: + cuda: ['12.4', '11.7'] + build: ['cuda'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }}-${{ matrix.cuda }}-${{ matrix.build }} + variant: sccache + evict-old-files: 1d + + - name: Install Cuda Toolkit 11.7 + if: ${{ matrix.cuda == '11.7' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-11.7.99-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-11.7.4.6-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-11.7.91-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-11.7.101-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-11.7.91-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cudart-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvcc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvrtc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libcublas-windows-x86_64-11.7.4.6-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvtx-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\visual_studio_integration-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvprof-windows-x86_64-11.7.101-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cccl-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V11_7=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Cuda Toolkit 12.4 + if: ${{ matrix.cuda == '12.4' }} + run: | + mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + choco install unzip -y + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-12.4.131-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-12.4.5.8-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-12.4.127-archive.zip" + curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-12.4.127-archive.zip" + unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cudart-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvcc-windows-x86_64-12.4.131-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvrtc-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libcublas-windows-x86_64-12.4.5.8-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvtx-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_profiler_api-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\visual_studio_integration-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvprof-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cccl-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V12_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Ninja + id: install_ninja + run: | + choco install ninja + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + shell: cmd + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ (github.event_name == 'push' && github.ref == 'refs/heads/master') || (github.event.inputs.create_release == 'true') }} + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\Release\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip .\build\bin\Release\* + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip + name: llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + - name: Copy and pack Cuda runtime + if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + run: | + echo "Cuda install location: ${{ env.CUDA_PATH }}" + $dst='.\build\bin\cudart\' + robocopy "${{env.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + robocopy "${{env.CUDA_PATH}}\lib" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + 7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip $dst\* + + - name: Upload Cuda runtime + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + name: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip + + windows-latest-cmake-sycl: + runs-on: windows-latest + + defaults: + run: + shell: bash + + env: + WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b380d914-366b-4b77-a74a-05e3c38b3514/intel-oneapi-base-toolkit-2025.0.0.882_offline.exe + WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel + ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI" + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-sycl + variant: sccache + evict-old-files: 1d + + - name: Install + run: | + scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL + + # TODO: add libcurl support ; we will also need to modify win-build-sycl.bat to accept user-specified args + + - name: Build + id: cmake_build + run: examples/sycl/win-build-sycl.bat + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Build the release package + id: pack_artifacts + if: ${{ (github.event_name == 'push' && github.ref == 'refs/heads/master') || (github.event.inputs.create_release == 'true') }} + run: | + echo "cp oneAPI running time dll files in ${{ env.ONEAPI_ROOT }} to ./build/bin" + + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_sycl_blas.5.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_core.2.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_tbb_thread.2.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_opencl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_loader.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_win_proxy_loader.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl8.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/svml_dispmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libmmd.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libiomp5md.dll" ./build/bin + + cp "${{ env.ONEAPI_ROOT }}/dnnl/latest/bin/dnnl.dll" ./build/bin + cp "${{ env.ONEAPI_ROOT }}/tbb/latest/bin/tbb12.dll" ./build/bin + + echo "cp oneAPI running time dll files to ./build/bin done" + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip ./build/bin/* + + - name: Upload the release package + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip + name: llama-bin-win-sycl-x64.zip + + windows-latest-cmake-hip: + if: ${{ github.event.inputs.create_release != 'true' }} + runs-on: windows-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }} + evict-old-files: 1d + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DGGML_HIP=ON ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + + # TODO: reuse windows-latest-cmake-hip instead of duplicating this job + windows-latest-cmake-hip-release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + runs-on: windows-latest + + strategy: + matrix: + gpu_target: [gfx1100, gfx1101, gfx1030] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Clone rocWMMA repository + id: clone_rocwmma + run: | + git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: windows-latest-cmake-hip-release + evict-old-files: 1d + + - name: Install + id: depends + run: | + $ErrorActionPreference = "Stop" + write-host "Downloading AMD HIP SDK Installer" + Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe" + write-host "Installing AMD HIP SDK" + Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait + write-host "Completed AMD HIP SDK installation" + + - name: Verify ROCm + id: verify + run: | + & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version + + - name: libCURL + id: get_libcurl + uses: ./.github/actions/windows-setup-curl + + - name: Build + id: cmake_build + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DAMDGPU_TARGETS=${{ matrix.gpu_target }} ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGGML_HIP=ON ` + -DGGML_RPC=ON ` + -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + md "build\bin\rocblas\library\" + cp "${env:HIP_PATH}\bin\hipblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas.dll" "build\bin\" + cp "${env:HIP_PATH}\bin\rocblas\library\*" "build\bin\rocblas\library\" + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + env: + CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} + run: | + cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\libcurl-x64.dll + 7z a llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip .\build\bin\* + + - name: Upload artifacts + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + name: llama-bin-win-hip-x64-${{ matrix.gpu_target }}.zip + + ios-xcode-build: + runs-on: macos-latest + + steps: + - name: Checkout code + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Build + id: cmake_build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DLLAMA_CURL=OFF \ + -DLLAMA_BUILD_EXAMPLES=OFF \ + -DLLAMA_BUILD_TESTS=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + - name: Build Xcode project + run: xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Pack artifacts + id: pack_artifacts + if: ${{ (github.event_name == 'push' && github.ref == 'refs/heads/master') || (github.event.inputs.create_release == 'true') }} + run: | + zip --symlinks -r llama-${{ steps.tag.outputs.name }}-xcframework.zip build-apple/llama.xcframework + + - name: Upload artifacts + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + uses: actions/upload-artifact@v4 + with: + path: llama-${{ steps.tag.outputs.name }}-xcframework.zip + name: llama-${{ steps.tag.outputs.name }}-xcframework + + android-build: + runs-on: ubuntu-latest + + steps: + - name: Clone + uses: actions/checkout@v4 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: android-build + evict-old-files: 1d + + - name: Set up JDK + uses: actions/setup-java@v3 + with: + java-version: 17 + distribution: zulu + + - name: Setup Android SDK + uses: android-actions/setup-android@v3 + with: + log-accepted-android-sdk-licenses: false + + - name: Build + run: | + cd examples/llama.android + + ./gradlew build --no-daemon + + release: + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + + runs-on: ubuntu-latest + + needs: + - ubuntu-cpu-cmake + - ubuntu-22-cmake-vulkan + - windows-latest-cmake + - windows-latest-cmake-cuda + - windows-latest-cmake-sycl + - windows-latest-cmake-hip-release + - macOS-latest-cmake-arm64 + - macOS-latest-cmake-x64 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: release + evict-old-files: 1d + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER="$(git rev-list --count HEAD)" + SHORT_HASH="$(git rev-parse --short=7 HEAD)" + if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT + fi + + - name: Download artifacts + id: download-artifact + uses: actions/download-artifact@v4 + with: + path: ./artifact + + - name: Move artifacts + id: move_artifacts + run: mkdir -p ./artifact/release && mv ./artifact/*/*.zip ./artifact/release + + - name: Create release + id: create_release + uses: ggml-org/action-create-release@v1 + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + with: + tag_name: ${{ steps.tag.outputs.name }} + + - name: Upload release + id: upload_release + uses: actions/github-script@v3 + with: + github-token: ${{secrets.GITHUB_TOKEN}} + script: | + const path = require('path'); + const fs = require('fs'); + const release_id = '${{ steps.create_release.outputs.id }}'; + for (let file of await fs.readdirSync('./artifact/release')) { + if (path.extname(file) === '.zip') { + console.log('uploadReleaseAsset', file); + await github.repos.uploadReleaseAsset({ + owner: context.repo.owner, + repo: context.repo.repo, + release_id: release_id, + name: file, + data: await fs.readFileSync(`./artifact/release/${file}`) + }); + } + } + +# ubuntu-latest-gcc: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-clang: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Debug, Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_COMPILER=clang +# +# - name: Build +# run: | +# make +# +# ubuntu-latest-gcc-sanitized: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# sanitizer: [ADDRESS, THREAD, UNDEFINED] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# sudo apt-get update +# sudo apt-get install build-essential +# sudo apt-get install cmake +# +# - name: Configure +# run: cmake . -DCMAKE_BUILD_TYPE=Debug -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON +# +# - name: Build +# run: | +# make +# +# windows: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# include: +# - arch: Win32 +# s2arc: x86 +# - arch: x64 +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Upload binaries +# uses: actions/upload-artifact@v4 +# with: +# name: llama-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# windows-blas: +# runs-on: windows-latest +# +# strategy: +# matrix: +# build: [Release] +# arch: [Win32, x64] +# blas: [ON] +# include: +# - arch: Win32 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x86.zip +# s2arc: x86 +# - arch: x64 +# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x64.zip +# s2arc: x64 +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Add msbuild to PATH +# uses: microsoft/setup-msbuild@v1 +# +# - name: Fetch OpenBLAS +# if: matrix.blas == 'ON' +# run: | +# C:/msys64/usr/bin/wget.exe -qO blas.zip ${{ matrix.obzip }} +# 7z x blas.zip -oblas -y +# copy blas/include/cblas.h . +# copy blas/include/openblas_config.h . +# echo "blasdir=$env:GITHUB_WORKSPACE/blas" >> $env:GITHUB_ENV +# +# - name: Configure +# run: > +# cmake -S . -B ./build -A ${{ matrix.arch }} +# -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# -DLLAMA_SUPPORT_OPENBLAS=${{ matrix.blas }} +# -DCMAKE_LIBRARY_PATH="$env:blasdir/lib" +# +# - name: Build +# run: | +# cd ./build +# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} +# +# - name: Copy libopenblas.dll +# if: matrix.blas == 'ON' +# run: copy "$env:blasdir/bin/libopenblas.dll" build/bin/${{ matrix.build }} +# +# - name: Upload binaries +# if: matrix.blas == 'ON' +# uses: actions/upload-artifact@v4 +# with: +# name: llama-blas-bin-${{ matrix.arch }} +# path: build/bin/${{ matrix.build }} +# +# emscripten: +# runs-on: ubuntu-latest +# +# strategy: +# matrix: +# build: [Release] +# +# steps: +# - name: Clone +# uses: actions/checkout@v4 +# +# - name: Dependencies +# run: | +# wget -q https://github.com/emscripten-core/emsdk/archive/master.tar.gz +# tar -xvf master.tar.gz +# emsdk-master/emsdk update +# emsdk-master/emsdk install latest +# emsdk-master/emsdk activate latest +# +# - name: Configure +# run: echo "tmp" +# +# - name: Build +# run: | +# pushd emsdk-master +# source ./emsdk_env.sh +# popd +# emcmake cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} +# make + + openEuler-latest-cmake-cann: + if: ${{ github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'Ascend NPU') }} + defaults: + run: + shell: bash -el {0} + runs-on: ubuntu-24.04-arm + strategy: + matrix: + cann: + - '8.1.RC1.alpha001-910b-openeuler22.03-py3.10' + device: + - 'ascend910b3' + build: + - 'Release' + container: ascendai/cann:${{ matrix.cann }} + steps: + - name: Checkout + uses: actions/checkout@v4 + + - name: Dependencies + run: | + yum update -y + yum install -y git gcc gcc-c++ make cmake libcurl-devel + + - name: Build + run: | + export LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/$(uname -m)-linux/devlib/:${LD_LIBRARY_PATH} + + cmake -S . -B build \ + -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ + -DGGML_CANN=on \ + -DSOC_TYPE=${{ matrix.device }} + cmake --build build -j $(nproc) diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index 1778bdde0ec47..76be7d6bd8be6 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -798,6 +798,7 @@ jobs: run: | cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS cmake --build build --config ${{ matrix.build }} -j $(nproc) + # Removed duplicate environment key "CURL_PATH" from this job to avoid conflicts. windows-latest-cmake: runs-on: windows-latest diff --git a/.gitignore b/.gitignore index 2c67ad7f7c609..c188ea503a80c 100644 --- a/.gitignore +++ b/.gitignore @@ -146,3 +146,5 @@ poetry.toml # Local scripts /run-vim.sh /run-chat.sh + +.fake \ No newline at end of file diff --git a/CMakePresets.json b/CMakePresets.json index cb7a9d31ea2c9..d2141f1baf71c 100644 --- a/CMakePresets.json +++ b/CMakePresets.json @@ -1,128 +1,17 @@ -<<<<<<< HEAD -{ -======= { ->>>>>>> master - "version": 4, - "configurePresets": [ - { - "name": "base", - "hidden": true, - "generator": "Ninja", - "binaryDir": "${sourceDir}/build-${presetName}", - "cacheVariables": { - "CMAKE_EXPORT_COMPILE_COMMANDS": "ON", - "CMAKE_INSTALL_RPATH": "$ORIGIN;$ORIGIN/.." + "version": 8, + "configurePresets": [ + { + "name": "Configure preset using toolchain file", + "displayName": "Configure preset using toolchain file", + "description": "Sets Ninja generator, build and install directory", + "generator": "Ninja", + "binaryDir": "${sourceDir}/out/build/${presetName}", + "cacheVariables": { + "CMAKE_BUILD_TYPE": "Debug", + "CMAKE_TOOLCHAIN_FILE": "", + "CMAKE_INSTALL_PREFIX": "${sourceDir}/out/install/${presetName}" + } } - }, -<<<<<<< HEAD - - { "name": "debug", "hidden": true, "cacheVariables": { "CMAKE_BUILD_TYPE": "Debug" } }, - { "name": "release", "hidden": true, "cacheVariables": { "CMAKE_BUILD_TYPE": "RelWithDebInfo" } }, - { "name": "static", "hidden": true, "cacheVariables": { "LLAMA_STATIC": "ON" } }, - - { - "name": "arm64-windows-msvc", "hidden": true, - "architecture": { "value": "arm64", "strategy": "external" }, - "toolset": { "value": "host=x86_64", "strategy": "external" }, -======= - { - "name": "sycl-base", - "hidden": true, - "generator": "Ninja", - "binaryDir": "${sourceDir}/build-${presetName}", - "cacheVariables": { - "CMAKE_EXPORT_COMPILE_COMMANDS": "ON", - "CMAKE_CXX_COMPILER": "icx", - "CMAKE_C_COMPILER": "cl", - "GGML_SYCL": "ON", - "CMAKE_INSTALL_RPATH": "$ORIGIN;$ORIGIN/.." - } - }, - { "name": "debug", "hidden": true, "cacheVariables": { "CMAKE_BUILD_TYPE": "Debug" } }, - { "name": "release", "hidden": true, "cacheVariables": { "CMAKE_BUILD_TYPE": "Release" } }, - { "name": "reldbg", "hidden": true, "cacheVariables": { "CMAKE_BUILD_TYPE": "RelWithDebInfo" } }, - { "name": "static", "hidden": true, "cacheVariables": { "GGML_STATIC": "ON" } }, - { "name": "sycl_f16", "hidden": true, "cacheVariables": { "GGML_SYCL_F16": "ON" } }, - { "name": "vulkan", "hidden": true, "cacheVariables": { "GGML_VULKAN": "ON" } }, - - { - "name": "x64-windows-llvm", "hidden": true, - "cacheVariables": { - "CMAKE_TOOLCHAIN_FILE": "${sourceDir}/cmake/x64-windows-llvm.cmake" - } - }, - - { - "name": "arm64-windows-msvc", "hidden": true, - "architecture": { "value": "arm64", "strategy": "external" }, - "toolset": { "value": "host=x64", "strategy": "external" }, ->>>>>>> master - "cacheVariables": { - "CMAKE_TOOLCHAIN_FILE": "${sourceDir}/cmake/arm64-windows-msvc.cmake" - } - }, - - { - "name": "arm64-windows-llvm", "hidden": true, -<<<<<<< HEAD - "architecture": { "value": "arm64", "strategy": "external" }, - "toolset": { "value": "host=x86_64", "strategy": "external" }, -======= - "architecture": { "value": "arm64", "strategy": "external" }, - "toolset": { "value": "host=x64", "strategy": "external" }, ->>>>>>> master - "cacheVariables": { - "CMAKE_TOOLCHAIN_FILE": "${sourceDir}/cmake/arm64-windows-llvm.cmake" - } - }, - -<<<<<<< HEAD - { "name": "arm64-windows-llvm-debug" , "inherits": [ "base", "arm64-windows-llvm", "debug" ] }, - { "name": "arm64-windows-llvm-release", "inherits": [ "base", "arm64-windows-llvm", "release" ] }, - { "name": "arm64-windows-llvm+static-release", "inherits": [ "base", "arm64-windows-llvm", "release", "static" ] }, - - { "name": "arm64-windows-msvc-debug" , "inherits": [ "base", "arm64-windows-msvc", "debug" ] }, - { "name": "arm64-windows-msvc-release", "inherits": [ "base", "arm64-windows-msvc", "release" ] }, - { "name": "arm64-windows-msvc+static-release", "inherits": [ "base", "arm64-windows-msvc", "release", "static" ] } -======= - { - "name": "arm64-apple-clang", "hidden": true, - "architecture": { "value": "arm64", "strategy": "external" }, - "toolset": { "value": "host=x64", "strategy": "external" }, - "cacheVariables": { - "CMAKE_TOOLCHAIN_FILE": "${sourceDir}/cmake/arm64-apple-clang.cmake" - } - }, - - { "name": "arm64-windows-llvm-debug", "inherits": [ "base", "arm64-windows-llvm", "debug" ] }, - { "name": "arm64-windows-llvm-release", "inherits": [ "base", "arm64-windows-llvm", "reldbg" ] }, - { "name": "arm64-windows-llvm+static-release", "inherits": [ "base", "arm64-windows-llvm", "reldbg", "static" ] }, - - { "name": "arm64-apple-clang-debug", "inherits": [ "base", "arm64-apple-clang", "debug" ] }, - { "name": "arm64-apple-clang-release", "inherits": [ "base", "arm64-apple-clang", "reldbg" ] }, - { "name": "arm64-apple-clang+static-release", "inherits": [ "base", "arm64-apple-clang", "reldbg", "static" ] }, - - { "name": "arm64-windows-msvc-debug", "inherits": [ "base", "arm64-windows-msvc", "debug" ] }, - { "name": "arm64-windows-msvc-release", "inherits": [ "base", "arm64-windows-msvc", "reldbg" ] }, - { "name": "arm64-windows-msvc+static-release", "inherits": [ "base", "arm64-windows-msvc", "reldbg", "static" ] }, - - { "name": "x64-windows-llvm-debug", "inherits": [ "base", "x64-windows-llvm", "debug" ] }, - { "name": "x64-windows-llvm-release", "inherits": [ "base", "x64-windows-llvm", "release" ] }, - { "name": "x64-windows-llvm-reldbg", "inherits": [ "base", "x64-windows-llvm", "reldbg" ] }, - { "name": "x64-windows-llvm+static-release", "inherits": [ "base", "x64-windows-llvm", "reldbg", "static" ] }, - - { "name": "x64-windows-msvc-debug", "inherits": [ "base", "debug" ] }, - { "name": "x64-windows-msvc-release", "inherits": [ "base", "reldbg" ] }, - { "name": "x64-windows-msvc+static-release", "inherits": [ "base", "reldbg", "static" ] }, - - { "name": "x64-windows-sycl-debug", "inherits": [ "sycl-base", "debug" ] }, - { "name": "x64-windows-sycl-debug-f16", "inherits": [ "sycl-base", "debug", "sycl_f16" ] }, - { "name": "x64-windows-sycl-release", "inherits": [ "sycl-base", "release" ] }, - { "name": "x64-windows-sycl-release-f16", "inherits": [ "sycl-base", "release", "sycl_f16" ] }, - - { "name": "x64-windows-vulkan-debug", "inherits": [ "base", "vulkan", "debug" ] }, - { "name": "x64-windows-vulkan-release", "inherits": [ "base", "vulkan", "release" ] } ->>>>>>> master - ] -} + ] +} \ No newline at end of file diff --git a/Untitled-1.json b/Untitled-1.json new file mode 100644 index 0000000000000..d8510496facdf --- /dev/null +++ b/Untitled-1.json @@ -0,0 +1,14 @@ +{ + "version": 3, + "configurePresets": [ + { + "name": "default", + "description": "Default build", + "generator": "Ninja", + "binaryDir": "build", + "cacheVariables": { + "CMAKE_BUILD_TYPE": "Release" + } + } + ] +} From aa1f4542362ec9a85e64d3d864e07c804eea80a7 Mon Sep 17 00:00:00 2001 From: Esra Korkmaz Date: Sat, 12 Apr 2025 03:25:21 +0300 Subject: [PATCH 10/11] Refactor CI workflow inputs and improve dispatch flexibility - Moved `push` input under unified `workflow_dispatch.inputs` - Improved readability and type consistency for boolean flags - Clarified purpose of CI in description block --- .github/workflows/build.yml | 60 ++++++++++++++++++++++++++----------- 1 file changed, 42 insertions(+), 18 deletions(-) diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index 76be7d6bd8be6..271a07164e5d5 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -1,13 +1,21 @@ name: CI +description: | + This workflow builds and tests the llama.cpp project on various platforms. + It is triggered on push, pull request, or manually via workflow_dispatch. + It also creates a release when a new commit is pushed to the master branch or when manually triggered. + The workflow includes jobs for macOS, Linux, and Windows, with different configurations and dependencies. + The workflow uses concurrency to cancel in-progress jobs if a new commit is pushed to the same branch. + It uses ccache to speed up the build process by caching compiled files. on: workflow_dispatch: # allows manual triggering inputs: create_release: + default: false description: 'Create new release' - required: true - type: boolean - push: + required: true + type: boolean + push: branches: - master paths: ['.github/workflows/build.yml', '.github/workflows/build-linux-cross.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp'] @@ -31,6 +39,7 @@ env: LLAMA_LOG_COLORS: 1 LLAMA_LOG_PREFIX: 1 LLAMA_LOG_TIMESTAMPS: 1 + CREATE_RELEASE: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' }} jobs: macOS-latest-cmake-arm64: @@ -89,13 +98,13 @@ jobs: - name: Pack artifacts id: pack_artifacts - if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + if: ${{ (github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true') || github.ref == 'refs/heads/master' }} run: | cp LICENSE ./build/bin/ zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip ./build/bin/* - name: Upload artifacts - if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} + if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || ( github.event_name == 'workflow_dispatch' && github.event.inputs.create_release == 'true' ) }} uses: actions/upload-artifact@v4 with: path: llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip @@ -723,7 +732,6 @@ jobs: with: key: macOS-latest-swift evict-old-files: 1d - - name: Dependencies id: depends continue-on-error: true @@ -782,6 +790,10 @@ jobs: mingw-w64-${{matrix.env}}-cmake mingw-w64-${{matrix.env}}-openblas + - name: Setup for build + run: | + echo "Setting up build environment" + - name: Build using CMake shell: msys2 {0} run: | @@ -927,14 +939,27 @@ jobs: id: get_libcurl uses: ./.github/actions/windows-setup-curl - - name: Build - id: cmake_build + - name: Build with libCURL + id: cmake_build_curl + shell: cmd env: CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }} run: | - cmake -S . -B build ${{ matrix.defines }} ` - -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" - cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS} + call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DLLAMA_BUILD_SERVER=ON ^ + -DGGML_NATIVE=OFF ^ + -DGGML_CUDA=ON ^ + -DGGML_RPC=ON ^ + -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config Release -j %NINJA_JOBS% -t ggml + cmake --build build --config Release + + - name: Copy libcurl DLL + id: copy_curl_dll + run: | + cp $env:RUNNER_TEMP/curl/bin/libcurl-x64.dll ./build/bin/Release/libcurl-x64.dll - name: Add libopenblas.dll id: add_libopenblas_dll @@ -959,14 +984,13 @@ jobs: - name: Test id: cmake_test # not all machines have native AVX-512 - if: ${{ matrix.build != 'arm64' && matrix.build != 'clblast' && matrix.build != 'kompute' && matrix.build != 'vulkan' && (matrix.build != 'avx512' || env.HAS_AVX512F == '1') }} + if: ${{ matrix.build != 'arm64' && matrix.build != 'clblast' && matrix.build != 'kompute' && matrix.build != 'vulkan' && (matrix.build != 'avx512' || steps.check_avx512f.outputs.has_avx512f == '1') }} run: | cd build ctest -L main -C Release --verbose --timeout 900 - name: Test (Intel SDE) - id: cmake_test_sde - if: ${{ matrix.build == 'avx512-x64' && env.HAS_AVX512F == '0' }} # use Intel SDE for AVX-512 emulation + if: ${{ matrix.build == 'avx512-x64' && steps.check_avx512f.outputs.has_avx512f == '0' }} # use Intel SDE for AVX-512 emulation run: | curl.exe -o $env:RUNNER_TEMP/sde.tar.xz -L "https://downloadmirror.intel.com/813591/sde-external-${env:SDE_VERSION}-win.tar.xz" # for some weird reason windows tar doesn't like sde tar.xz @@ -1142,10 +1166,10 @@ jobs: - name: Copy and pack Cuda runtime if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} run: | - echo "Cuda install location: ${{ env.CUDA_PATH }}" + echo "Cuda install location: $CUDA_PATH" $dst='.\build\bin\cudart\' - robocopy "${{env.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll - robocopy "${{env.CUDA_PATH}}\lib" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + robocopy "$env:CUDA_PATH\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll + robocopy "$env:CUDA_PATH\lib" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll 7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip $dst\* - name: Upload Cuda runtime @@ -1487,7 +1511,7 @@ jobs: - ubuntu-cpu-cmake - ubuntu-22-cmake-vulkan - windows-latest-cmake - - windows-2019-cmake-cuda + - windows-latest-cmake-cuda - windows-latest-cmake-sycl - windows-latest-cmake-hip-release - macOS-latest-cmake-arm64 From a6ee23cc9067bdbfe25b3d6f2b6922b94fb54284 Mon Sep 17 00:00:00 2001 From: Esra Korkmaz Date: Sun, 29 Jun 2025 18:09:55 +0300 Subject: [PATCH 11/11] Merge branch 'master' into pr/7191 --- kompute | 1 + 1 file changed, 1 insertion(+) create mode 160000 kompute diff --git a/kompute b/kompute new file mode 160000 index 0000000000000..4565194ed7c32 --- /dev/null +++ b/kompute @@ -0,0 +1 @@ +Subproject commit 4565194ed7c32d1d2efa32ceab4d3c6cae006306