1 file changed
+1
-1
lines changed- .devops/cuda.Dockerfile+1-1
- .devops/intel.Dockerfile+1-1
- .devops/llama-cli-cann.Dockerfile+2-2
- .devops/musa.Dockerfile+1-1
- .devops/rocm.Dockerfile+3-3
- .devops/vulkan.Dockerfile+1-1
- .github/workflows/build.yml+5-4
- .github/workflows/docker.yml+6-6
- Makefile-4
- README.md+5-8
- build-xcframework.sh+16-4
- common/arg.cpp+10-9
- common/chat.cpp+1-1
- common/common.cpp+17-2
- common/common.h+2
- convert_hf_to_gguf.py+110-15
- convert_hf_to_gguf_update.py+1
- docs/backend/SYCL.md+4-4
- docs/build.md+4-2
- examples/llava/CMakeLists.txt+32-1
- examples/llava/clip-impl.h+71
- examples/llava/clip.cpp+186-185
- examples/llava/clip.h+21-15
- examples/llava/gemma3-cli.cpp+88-111
- examples/llava/llava.cpp+57-46
- examples/llava/mtmd.cpp+341
- examples/llava/mtmd.h+146
- examples/quantize/quantize.cpp+115-2
- examples/rpc/rpc-server.cpp+4-2
- examples/run/run.cpp+4-2
- examples/server/public/index.html.gz
- examples/server/server.cpp+36-3
- examples/server/tests/unit/test_embedding.py+20
- examples/server/tests/utils.py+15
- examples/server/webui/src/components/ChatScreen.tsx+13-45
- examples/server/webui/src/components/useChatTextarea.ts+96
- examples/server/webui/src/utils/llama-vscode.ts+2-2
- examples/server_embd.py+1-1
- examples/sycl/build.sh+2-2
- ggml/CMakeLists.txt-1
- ggml/include/ggml.h+38-91
- ggml/src/ggml-cann/acl_tensor.cpp+2
- ggml/src/ggml-cann/aclnn_ops.cpp+229-123
- ggml/src/ggml-cann/aclnn_ops.h+174-56
- ggml/src/ggml-cann/ggml-cann.cpp+382-70
- ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp+809-101
- ggml/src/ggml-cpu/ggml-cpu-impl.h-2
- ggml/src/ggml-cpu/ggml-cpu.c+15-40
- ggml/src/ggml-cpu/ggml-cpu.cpp+2
- ggml/src/ggml-cpu/ops.cpp+84-166
- ggml/src/ggml-cpu/ops.h+1-20
- ggml/src/ggml-cpu/simd-mappings.h+11-3
- ggml/src/ggml-cuda/cpy.cu+21
- ggml/src/ggml-cuda/ggml-cuda.cu+22-17
- ggml/src/ggml-cuda/vendors/hip.h+2
- ggml/src/ggml-hip/CMakeLists.txt-4
- ggml/src/ggml-impl.h+20-13
- ggml/src/ggml-metal/ggml-metal.m+40-2
- ggml/src/ggml-metal/ggml-metal.metal+10
- ggml/src/ggml-rpc/ggml-rpc.cpp+23-22
- ggml/src/ggml-sycl/element_wise.cpp+730-235
- ggml/src/ggml-sycl/element_wise.hpp+24
- ggml/src/ggml-sycl/ggml-sycl.cpp+22-59
- ggml/src/ggml-sycl/im2col.cpp+82-67
- ggml/src/ggml-sycl/rope.cpp+103-3
- ggml/src/ggml-vulkan/ggml-vulkan.cpp+10-3
- ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs_cm2.comp+113-3
- ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_cm2.comp+11-6
- ggml/src/ggml-vulkan/vulkan-shaders/mul_mm_cm2.comp+116-39
- ggml/src/ggml.c+80-198
- gguf-py/gguf/constants.py+65
- gguf-py/gguf/gguf_writer.py+6
- gguf-py/gguf/tensor_mapping.py+32-3
- gguf-py/gguf/utility.py+195
- include/llama.h+12-11
- scripts/sync-ggml-am.sh+12-12
- scripts/sync-ggml.last+1-1
- src/llama-arch.cpp+67-17
- src/llama-arch.h+9
- src/llama-context.cpp+12-3
- src/llama-graph.cpp+23-5
- src/llama-graph.h+7-3
- src/llama-hparams.h+4
- src/llama-kv-cache.cpp+1-1
- src/llama-model.cpp+801-195
- src/llama-model.h+2
- src/llama-quant.cpp+28-7
- src/llama-vocab.cpp+1
- tests/test-backend-ops.cpp+25-11
- tests/test-chat.cpp+9
0 commit comments