Update links, remove ccache and curl

Author: EZForever

.github/workflows/build-oneapi.yml

@@ -30,7 +30,7 @@ jobs:
       - name: Checkout llama.cpp
         uses: actions/checkout@v4
         with:
-          repository: ggerganov/llama.cpp
+          repository: ggml-org/llama.cpp
           path: repo
 
       - name: Get number of CPU cores
@@ -44,12 +44,12 @@ jobs:
           wget -q -O - https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | sudo gpg --dearmor --output /etc/apt/trusted.gpg.d/oneapi.gpg
           echo 'deb [trusted=yes] https://apt.repos.intel.com/oneapi all main' | sudo tee /etc/apt/sources.list.d/oneapi.list >/dev/null
           sudo apt-get update
-          sudo apt-get install -y intel-oneapi-compiler-dpcpp-cpp cmake git ccache
+          sudo apt-get install -y intel-oneapi-compiler-dpcpp-cpp cmake git
 
       - name: CMake
         run: |
           . /opt/intel/oneapi/setvars.sh
-          cmake repo -B build -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DCMAKE_C_FLAGS="-Ofast -xCORE-AVX2" -DCMAKE_CXX_FLAGS="-Ofast -xCORE-AVX2" -DCMAKE_EXE_LINKER_FLAGS="-static" -DGGML_NATIVE=OFF -DGGML_STATIC=ON -DGGML_RPC=ON -DGGML_OPENMP=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=OFF
+          cmake repo -B build -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DCMAKE_C_FLAGS="-Ofast -xCORE-AVX2" -DCMAKE_CXX_FLAGS="-Ofast -xCORE-AVX2" -DCMAKE_EXE_LINKER_FLAGS="-static" -DGGML_NATIVE=OFF -DGGML_STATIC=ON -DGGML_RPC=ON -DGGML_CCACHE=OFF -DGGML_OPENMP=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CURL=OFF -DBUILD_SHARED_LIBS=OFF
           cmake --build build --config Release --target llama-server --target rpc-server -j ${{ steps.cpu-cores.outputs.count }}
           strip build/bin/*
 

.github/workflows/build.yml

@@ -44,7 +44,7 @@ jobs:
       - name: Checkout llama.cpp
         uses: actions/checkout@v4
         with:
-          repository: ggerganov/llama.cpp
+          repository: ggml-org/llama.cpp
           path: repo
 
       - name: Get number of CPU cores
@@ -54,11 +54,11 @@ jobs:
       - name: Setup Alpine Linux
         uses: jirutka/setup-alpine@v1
         with:
-          packages: build-base cmake ccache git openssl-dev openssl-libs-static
+          packages: build-base cmake git openssl-dev openssl-libs-static
 
       - name: CMake
         run: |
-          cmake repo -B build -DCMAKE_BUILD_TYPE=Release -DCMAKE_EXE_LINKER_FLAGS="-static" -DGGML_NATIVE=OFF -DGGML_STATIC=ON -DGGML_RPC=ON -DGGML_OPENMP=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=OFF ${{ matrix.ssl_defines }} ${{ matrix.avx_defines }}
+          cmake repo -B build -DCMAKE_BUILD_TYPE=Release -DCMAKE_EXE_LINKER_FLAGS="-static" -DGGML_NATIVE=OFF -DGGML_STATIC=ON -DGGML_RPC=ON -DGGML_CCACHE=OFF -DGGML_OPENMP=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CURL=OFF -DBUILD_SHARED_LIBS=OFF ${{ matrix.ssl_defines }} ${{ matrix.avx_defines }}
           cmake --build build --config Release --target llama-server --target rpc-server -j ${{ steps.cpu-cores.outputs.count }}
           strip build/bin/*
         shell: alpine.sh {0}

README.md

@@ -1,12 +1,12 @@
 # llama.cpp-static
 Your daily, minimal build of llama.cpp. [Also available on Docker Hub.](https://hub.docker.com/r/ezforever/llama.cpp-static)
 
-Source code: <https://github.com/ggerganov/llama.cpp>  
+Source code: <https://github.com/ggml-org/llama.cpp>
 Built from: <https://github.com/EZForever/llama.cpp-static>
 
 ## Usage
 
-Please refer to [llama.cpp docker guide](https://github.com/ggerganov/llama.cpp/blob/master/README.md#docker) and [server README](https://github.com/ggerganov/llama.cpp/tree/master/examples/server).
+Please refer to [llama.cpp docker guide](https://github.com/ggml-org/llama.cpp/blob/master/docs/docker.md) and [server README](https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md).
 
 ## Tag format
 
@@ -25,7 +25,7 @@ Server images are tagged in the format of `server-<ssl>-<avx>`.
 - `avx`: (Only) AVX instruction set is enabled. Might be useful if you are using some old CPUs that don't support AVX2.
 - `avx2`: AVX2 instruction set is enabled. This build should support most modern/recent CPUs with reasonable performance.
 - `avx512`: AVX512 base instruction set is enabled. Currently only some high-end or server-grade CPUs support this instruction set, so check your hardware specs before using this build.
-- `oneapi`: Experimental build with the Intel oneAPI compiler, inspired by ggerganov/llama.cpp#5067. Offers a ~30% speed increase (~20tok/s vs ~15tok/s) in prompt processing on my machine compared to `avx2` builds. Not updated daily.
+- `oneapi`: Experimental build with the Intel oneAPI compiler, inspired by ggml-org/llama.cpp#5067. Offers a ~30% speed increase (~20tok/s vs ~15tok/s) in prompt processing on my machine compared to `avx2` builds. Not updated daily.
 
-RPC server images are tagged in the format of `rpc-server-<ssl>-<avx>`. Refer to [rpc README](https://github.com/ggerganov/llama.cpp/tree/master/examples/rpc) for detailed information.
+RPC server images are tagged in the format of `rpc-server-<ssl>-<avx>`. Refer to [rpc README](https://github.com/ggml-org/llama.cpp/blob/master/tools/rpc/README.md) for detailed information.