summaryrefslogtreecommitdiff
path: root/llama.cpp/.github/workflows/build.yml
diff options
context:
space:
mode:
Diffstat (limited to 'llama.cpp/.github/workflows/build.yml')
-rw-r--r--llama.cpp/.github/workflows/build.yml2138
1 files changed, 2138 insertions, 0 deletions
diff --git a/llama.cpp/.github/workflows/build.yml b/llama.cpp/.github/workflows/build.yml
new file mode 100644
index 0000000..6c7ab71
--- /dev/null
+++ b/llama.cpp/.github/workflows/build.yml
@@ -0,0 +1,2138 @@
+name: CI
+
+on:
+ workflow_dispatch: # allows manual triggering
+ push:
+ branches:
+ - master
+ paths: [
+ '.github/workflows/build.yml',
+ '.github/workflows/build-linux-cross.yml',
+ '.github/workflows/build-cmake-pkg.yml',
+ '**/CMakeLists.txt',
+ '**/.cmake',
+ '**/*.h',
+ '**/*.hpp',
+ '**/*.c',
+ '**/*.cpp',
+ '**/*.cu',
+ '**/*.cuh',
+ '**/*.swift',
+ '**/*.m',
+ '**/*.metal',
+ '**/*.comp',
+ '**/*.glsl',
+ '**/*.wgsl'
+ ]
+
+ pull_request:
+ types: [opened, synchronize, reopened]
+ paths: [
+ '.github/workflows/build.yml',
+ '.github/workflows/build-linux-cross.yml',
+ '.github/workflows/build-cmake-pkg.yml',
+ '**/CMakeLists.txt',
+ '**/.cmake',
+ '**/*.h',
+ '**/*.hpp',
+ '**/*.c',
+ '**/*.cpp',
+ '**/*.cu',
+ '**/*.cuh',
+ '**/*.swift',
+ '**/*.m',
+ '**/*.metal',
+ '**/*.comp',
+ '**/*.glsl',
+ '**/*.wgsl'
+ ]
+
+concurrency:
+ group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
+ cancel-in-progress: true
+
+env:
+ GGML_NLOOP: 3
+ GGML_N_THREADS: 1
+ LLAMA_LOG_COLORS: 1
+ LLAMA_LOG_PREFIX: 1
+ LLAMA_LOG_TIMESTAMPS: 1
+
+jobs:
+ macOS-latest-cmake-arm64:
+ runs-on: macos-latest
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: macOS-latest-cmake-arm64
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Build
+ id: cmake_build
+ run: |
+ sysctl -a
+ cmake -B build \
+ -DCMAKE_BUILD_RPATH="@loader_path" \
+ -DLLAMA_FATAL_WARNINGS=ON \
+ -DLLAMA_BUILD_BORINGSSL=ON \
+ -DGGML_METAL_USE_BF16=ON \
+ -DGGML_METAL_EMBED_LIBRARY=OFF \
+ -DGGML_METAL_SHADER_DEBUG=ON \
+ -DGGML_RPC=ON
+ cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
+ leaks -atExit -- ./build/bin/test-thread-safety -hf ggml-org/gemma-3-270m-qat-GGUF -ngl 99 -p "$(printf 'hello %.0s' {1..128})" -n 16 -c 512 -ub 32 -np 2 -t 2 -lv 1
+
+ - name: Test
+ id: cmake_test
+ run: |
+ cd build
+ ctest -L main --verbose --timeout 900
+
+ macOS-latest-cmake-x64:
+ runs-on: macos-15-intel
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: macOS-latest-cmake-x64
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - 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 \
+ -DLLAMA_BUILD_BORINGSSL=ON \
+ -DGGML_METAL=OFF \
+ -DGGML_RPC=ON \
+ -DCMAKE_OSX_DEPLOYMENT_TARGET=13.3
+ cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
+
+ - name: Test
+ id: cmake_test
+ run: |
+ cd build
+ ctest -L main --verbose --timeout 900
+
+ macOS-latest-cmake-arm64-webgpu:
+ runs-on: macos-latest
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: macOS-latest-cmake-arm64-webgpu
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Dawn Dependency
+ id: dawn-depends
+ run: |
+ DAWN_VERSION="v2.0.0"
+ DAWN_OWNER="reeselevine"
+ DAWN_REPO="dawn"
+ DAWN_ASSET_NAME="Dawn-5e9a4865b1635796ccc77dd30057f2b4002a1355-macos-latest-Release"
+ echo "Fetching release asset from https://github.com/${DAWN_OWNER}/${DAWN_REPO}/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.zip"
+ curl -L -o artifact.zip \
+ "https://github.com/${DAWN_OWNER}/${DAWN_REPO}/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.zip"
+ mkdir dawn
+ unzip artifact.zip
+ tar -xvf ${DAWN_ASSET_NAME}.tar.gz -C dawn --strip-components=1
+
+ - name: Build
+ id: cmake_build
+ run: |
+ export CMAKE_PREFIX_PATH=dawn
+ cmake -B build -DGGML_WEBGPU=ON -DGGML_METAL=OFF -DGGML_BLAS=OFF
+ cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
+
+ - name: Test
+ id: cmake_test
+ run: |
+ cd build
+ ctest -L main --verbose --timeout 900
+
+ ubuntu-cpu-cmake:
+ strategy:
+ matrix:
+ include:
+ - build: 'x64'
+ os: ubuntu-22.04
+ - build: 'arm64'
+ os: ubuntu-22.04-arm
+ - build: 's390x'
+ os: ubuntu-24.04-s390x
+ - build: 'ppc64le'
+ os: ubuntu-24.04-ppc64le
+
+ runs-on: ${{ matrix.os }}
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ubuntu-cpu-cmake-${{ matrix.build }}
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Build Dependencies
+ id: build_depends
+ run: |
+ sudo apt-get update
+ sudo apt-get install -y --no-install-recommends \
+ python3 python3-pip python3-dev \
+ libjpeg-dev build-essential libssl-dev \
+ git-lfs
+
+ - name: Python Dependencies
+ id: python_depends
+ run: |
+ python3 -m pip install --upgrade pip
+ pip3 install ./gguf-py
+
+ - name: Swap Endianness
+ id: endianness
+ if: ${{ matrix.build == 's390x' }}
+ run: |
+ for f in models/*.gguf; do
+ echo YES | python3 gguf-py/gguf/scripts/gguf_convert_endian.py $f big
+ done
+
+ - 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 --verbose --timeout 900
+
+ - name: Test llama2c conversion
+ id: llama2c_test
+ if: ${{ matrix.build != 's390x' }}
+ 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-completion -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
+
+ - name: Test llama2c (s390x)
+ id: llama2c_test_s390x
+ if: ${{ matrix.build == 's390x' }}
+ run: |
+ cd build
+ echo "Fetch llama2c big-endian model"
+ wget https://huggingface.co/ggml-org/models/resolve/main/tinyllamas/stories260K-be.gguf
+ ./bin/llama-completion -m stories260K-be.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
+
+ ubuntu-latest-cmake-sanitizer:
+ runs-on: ubuntu-latest
+
+ continue-on-error: true
+
+ strategy:
+ matrix:
+ sanitizer: [ADDRESS, THREAD, UNDEFINED]
+ build_type: [Debug]
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ubuntu-latest-cmake-sanitizer-${{ matrix.sanitizer }}
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Dependencies
+ id: depends
+ run: |
+ sudo apt-get update
+ sudo apt-get install build-essential libssl-dev
+
+ - name: Build
+ id: cmake_build
+ if: ${{ matrix.sanitizer != 'THREAD' }}
+ run: |
+ cmake -B build \
+ -DLLAMA_FATAL_WARNINGS=ON \
+ -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
+ -DGGML_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 \
+ -DGGML_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@v6
+
+ - name: Dependencies
+ id: depends
+ run: |
+ sudo apt-get update
+ sudo apt-get install build-essential libssl-dev
+
+ - name: Build
+ id: cmake_build
+ run: |
+ cmake -B build \
+ -DLLAMA_FATAL_WARNINGS=ON \
+ -DLLAMA_LLGUIDANCE=ON
+ cmake --build 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@v6
+
+ # - name: ccache
+ # uses: ggml-org/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 libssl-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-24-cmake-vulkan-deb:
+ runs-on: ubuntu-24.04
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ubuntu-24-cmake-vulkan-deb
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Dependencies
+ id: depends
+ run: |
+ sudo apt-get install -y glslc libvulkan-dev libssl-dev
+
+ - name: Configure
+ id: cmake_configure
+ run: |
+ cmake -B build \
+ -DCMAKE_BUILD_TYPE=RelWithDebInfo \
+ -DGGML_BACKEND_DL=ON \
+ -DGGML_CPU_ALL_VARIANTS=ON \
+ -DGGML_VULKAN=ON
+
+ - name: Build
+ id: cmake_build
+ run: |
+ cmake --build build -j $(nproc)
+
+ ubuntu-24-cmake-vulkan:
+ runs-on: ubuntu-24.04
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ubuntu-24-cmake-vulkan
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Dependencies
+ id: depends
+ run: |
+ sudo add-apt-repository -y ppa:kisak/kisak-mesa
+ sudo apt-get update -y
+ sudo apt-get install -y build-essential mesa-vulkan-drivers libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libssl-dev
+
+ - name: Get latest Vulkan SDK version
+ id: vulkan_sdk_version
+ run: |
+ echo "VULKAN_SDK_VERSION=$(curl https://vulkan.lunarg.com/sdk/latest/linux.txt)" >> "$GITHUB_ENV"
+
+ - name: Use Vulkan SDK Cache
+ uses: actions/cache@v5
+ id: cache-sdk
+ with:
+ path: ./vulkan_sdk
+ key: vulkan-sdk-${{ env.VULKAN_SDK_VERSION }}-${{ runner.os }}
+
+ - name: Setup Vulkan SDK
+ if: steps.cache-sdk.outputs.cache-hit != 'true'
+ uses: ./.github/actions/linux-setup-vulkan
+ with:
+ path: ./vulkan_sdk
+ version: ${{ env.VULKAN_SDK_VERSION }}
+
+ - name: Build
+ id: cmake_build
+ run: |
+ source ./vulkan_sdk/setup-env.sh
+ cmake -B build \
+ -DGGML_VULKAN=ON
+ cmake --build build --config Release -j $(nproc)
+
+ - name: Test
+ id: cmake_test
+ run: |
+ cd build
+ export GGML_VK_VISIBLE_DEVICES=0
+ export GGML_VK_DISABLE_F16=1
+ # This is using llvmpipe and runs slower than other backends
+ ctest -L main --verbose --timeout 4800
+
+ ubuntu-24-cmake-webgpu:
+ runs-on: ubuntu-24.04
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ubuntu-24-cmake-webgpu
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Dependencies
+ id: depends
+ run: |
+ sudo add-apt-repository -y ppa:kisak/kisak-mesa
+ sudo apt-get update -y
+ sudo apt-get install -y build-essential mesa-vulkan-drivers libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libssl-dev
+
+ - name: Get latest Vulkan SDK version
+ id: vulkan_sdk_version
+ run: |
+ echo "VULKAN_SDK_VERSION=$(curl https://vulkan.lunarg.com/sdk/latest/linux.txt)" >> "$GITHUB_ENV"
+
+ - name: Use Vulkan SDK Cache
+ uses: actions/cache@v5
+ id: cache-sdk
+ with:
+ path: ./vulkan_sdk
+ key: vulkan-sdk-${{ env.VULKAN_SDK_VERSION }}-${{ runner.os }}
+
+ - name: Setup Vulkan SDK
+ if: steps.cache-sdk.outputs.cache-hit != 'true'
+ uses: ./.github/actions/linux-setup-vulkan
+ with:
+ path: ./vulkan_sdk
+ version: ${{ env.VULKAN_SDK_VERSION }}
+
+ - name: Dawn Dependency
+ id: dawn-depends
+ run: |
+ sudo apt-get install -y libxrandr-dev libxinerama-dev libxcursor-dev mesa-common-dev libx11-xcb-dev libxi-dev
+ DAWN_VERSION="v2.0.0"
+ DAWN_OWNER="reeselevine"
+ DAWN_REPO="dawn"
+ DAWN_ASSET_NAME="Dawn-5e9a4865b1635796ccc77dd30057f2b4002a1355-ubuntu-latest-Release"
+ echo "Fetching release asset from https://github.com/${DAWN_OWNER}/${DAWN_REPO}/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.zip"
+ curl -L -o artifact.zip \
+ "https://github.com/${DAWN_OWNER}/${DAWN_REPO}/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.zip"
+ mkdir dawn
+ unzip artifact.zip
+ tar -xvf ${DAWN_ASSET_NAME}.tar.gz -C dawn --strip-components=1
+
+ - name: Build
+ id: cmake_build
+ run: |
+ export Dawn_DIR=dawn/lib64/cmake/Dawn
+ cmake -B build \
+ -DGGML_WEBGPU=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 3600
+
+ ubuntu-24-wasm-webgpu:
+ runs-on: ubuntu-24.04
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ubuntu-latest-wasm-webgpu
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Install Emscripten
+ run: |
+ git clone https://github.com/emscripten-core/emsdk.git
+ cd emsdk
+ ./emsdk install latest
+ ./emsdk activate latest
+
+ - name: Fetch emdawnwebgpu
+ run: |
+ DAWN_TAG="v20251027.212519"
+ EMDAWN_PKG="emdawnwebgpu_pkg-${DAWN_TAG}.zip"
+ echo "Downloading ${EMDAWN_PKG}"
+ curl -L -o emdawn.zip \
+ "https://github.com/google/dawn/releases/download/${DAWN_TAG}/${EMDAWN_PKG}"
+ unzip emdawn.zip
+
+ - name: Build WASM WebGPU
+ run: |
+ source emsdk/emsdk_env.sh
+ emcmake cmake -B build-wasm \
+ -DGGML_WEBGPU=ON \
+ -DLLAMA_OPENSSL=OFF \
+ -DEMDAWNWEBGPU_DIR=emdawnwebgpu_pkg
+
+ cmake --build build-wasm --target test-backend-ops -j $(nproc)
+
+ ubuntu-22-cmake-hip:
+ runs-on: ubuntu-22.04
+ container: rocm/dev-ubuntu-22.04:6.1.2
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Dependencies
+ id: depends
+ run: |
+ sudo apt-get update
+ sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libssl-dev rocwmma-dev
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ubuntu-22-cmake-hip
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Build with native CMake HIP support
+ id: cmake_build
+ run: |
+ cmake -B build -S . \
+ -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \
+ -DGGML_HIP_ROCWMMA_FATTN=ON \
+ -DGGML_HIP=ON
+ cmake --build build --config Release -j $(nproc)
+
+ ubuntu-22-cmake-musa:
+ runs-on: ubuntu-22.04
+ container: mthreads/musa:rc4.3.0-devel-ubuntu22.04-amd64
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Dependencies
+ id: depends
+ run: |
+ apt-get update
+ apt-get install -y build-essential git cmake libssl-dev
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ubuntu-22-cmake-musa
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - 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@v6
+
+ - 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 libssl-dev
+
+ - name: install oneAPI MKL library
+ shell: bash
+ run: |
+ sudo apt install intel-oneapi-mkl-devel
+
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ubuntu-22-cmake-sycl
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - 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@v6
+
+ - 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 libssl-dev
+
+ - name: install oneAPI MKL library
+ shell: bash
+ run: |
+ sudo apt install intel-oneapi-mkl-devel
+
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ubuntu-22-cmake-sycl-fp16
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - 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
+
+ build-cmake-pkg:
+ uses: ./.github/workflows/build-cmake-pkg.yml
+
+ macOS-latest-cmake-ios:
+ runs-on: macos-latest
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: macOS-latest-cmake-ios
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - 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_TOOLS=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@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: macOS-latest-cmake-tvos
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - 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_TOOLS=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@v6
+
+ - 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_TOOLS=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
+ needs: ios-xcode-build
+
+ strategy:
+ matrix:
+ destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS']
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: macOS-latest-swift
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Download xcframework artifact
+ uses: actions/download-artifact@v7
+ with:
+ name: llama-xcframework
+ path: build-apple/llama.xcframework/
+
+ - 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_OPENSSL=OFF \
+ -DLLAMA_BUILD_EXAMPLES=OFF \
+ -DLLAMA_BUILD_TOOLS=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)
+
+ windows-msys2:
+ runs-on: windows-2025
+
+ 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@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: windows-msys2
+ variant: ccache
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - 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: 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 $(nproc)
+
+ windows-latest-cmake:
+ runs-on: windows-2025
+
+ env:
+ OPENBLAS_VERSION: 0.3.23
+ SDE_VERSION: 9.33.0-2024-01-07
+ VULKAN_VERSION: 1.4.313.2
+
+ strategy:
+ matrix:
+ include:
+ - build: 'cpu-x64 (static)'
+ arch: 'x64'
+ defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DBUILD_SHARED_LIBS=OFF'
+ - build: 'openblas-x64'
+ arch: 'x64'
+ defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_OPENMP=OFF -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
+ - build: 'vulkan-x64'
+ arch: 'x64'
+ defines: '-DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_VULKAN=ON'
+ - build: 'llvm-arm64'
+ arch: 'arm64'
+ defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON'
+ - build: 'llvm-arm64-opencl-adreno'
+ arch: 'arm64'
+ defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" -DGGML_OPENCL=ON -DGGML_OPENCL_USE_ADRENO_KERNELS=ON'
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: windows-latest-cmake-${{ matrix.build }}
+ variant: ccache
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - 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 == 'vulkan-x64' }}
+ run: |
+ curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/vulkansdk-windows-X64-${env:VULKAN_VERSION}.exe"
+ & "$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: Install OpenCL Headers and Libs
+ id: install_opencl
+ if: ${{ matrix.build == 'llvm-arm64-opencl-adreno' }}
+ run: |
+ git clone https://github.com/KhronosGroup/OpenCL-Headers
+ cd OpenCL-Headers
+ cmake -B build `
+ -DBUILD_TESTING=OFF `
+ -DOPENCL_HEADERS_BUILD_TESTING=OFF `
+ -DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF `
+ -DCMAKE_INSTALL_PREFIX="$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: Build
+ id: cmake_build
+ run: |
+ cmake -S . -B build ${{ matrix.defines }} `
+ -DLLAMA_BUILD_BORINGSSL=ON
+ cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS}
+
+ - 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: Test
+ id: cmake_test
+ if: ${{ matrix.arch == 'x64' }}
+ run: |
+ cd build
+ ctest -L main -C Release --verbose --timeout 900
+
+ # TODO: disabled for now, consider adding tests for all CPU variants instead
+ # - name: Test (Intel SDE)
+ # id: cmake_test_sde
+ # 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
+
+ ubuntu-latest-cmake-cuda:
+ runs-on: ubuntu-latest
+ container: nvidia/cuda:12.6.2-devel-ubuntu24.04
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Install dependencies
+ env:
+ DEBIAN_FRONTEND: noninteractive
+ run: |
+ apt update
+ apt install -y cmake build-essential ninja-build libgomp1 git libssl-dev
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ubuntu-latest-cmake-cuda
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Build with CMake
+ # TODO: Remove GGML_CUDA_CUB_3DOT2 flag once CCCL 3.2 is bundled within CTK and that CTK version is used in this project
+ run: |
+ cmake -S . -B build -G Ninja \
+ -DLLAMA_FATAL_WARNINGS=ON \
+ -DCMAKE_BUILD_TYPE=Release \
+ -DCMAKE_CUDA_ARCHITECTURES=89-real \
+ -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined \
+ -DGGML_NATIVE=OFF \
+ -DGGML_CUDA=ON \
+ -DGGML_CUDA_CUB_3DOT2=ON
+ cmake --build build
+
+ windows-2022-cmake-cuda:
+ runs-on: windows-2022
+
+ strategy:
+ matrix:
+ cuda: ['12.4']
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Install ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: windows-cuda-${{ matrix.cuda }}
+ variant: ccache
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Install Cuda Toolkit
+ uses: ./.github/actions/windows-setup-cuda
+ with:
+ cuda_version: ${{ matrix.cuda }}
+
+ - name: Install Ninja
+ id: install_ninja
+ run: |
+ choco install ninja
+
+ - name: Build
+ id: cmake_build
+ shell: cmd
+ # TODO: Remove GGML_CUDA_CUB_3DOT2 flag once CCCL 3.2 is bundled within CTK and that CTK version is used in this project
+ run: |
+ call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvarsall.bat" x64
+ cmake -S . -B build -G "Ninja Multi-Config" ^
+ -DLLAMA_BUILD_SERVER=ON ^
+ -DLLAMA_BUILD_BORINGSSL=ON ^
+ -DGGML_NATIVE=OFF ^
+ -DGGML_BACKEND_DL=ON ^
+ -DGGML_CPU_ALL_VARIANTS=ON ^
+ -DGGML_CUDA=ON ^
+ -DGGML_RPC=ON ^
+ -DGGML_CUDA_CUB_3DOT2=ON
+ set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
+ cmake --build build --config Release -j %NINJA_JOBS% -t ggml
+ cmake --build build --config Release
+
+ windows-latest-cmake-sycl:
+ runs-on: windows-2022
+
+ defaults:
+ run:
+ shell: bash
+
+ env:
+ WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/24751ead-ddc5-4479-b9e6-f9fe2ff8b9f2/intel-deep-learning-essentials-2025.2.1.25_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@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: windows-latest-cmake-sycl
+ variant: ccache
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Install
+ run: |
+ scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL
+
+ # TODO: add ssl support ; we will also need to modify win-build-sycl.bat to accept user-specified args
+
+ - name: Build
+ id: cmake_build
+ run: examples/sycl/win-build-sycl.bat
+
+ windows-latest-cmake-hip:
+ runs-on: windows-2022
+
+ env:
+ # The ROCm version must correspond to the version used in the HIP SDK.
+ ROCM_VERSION: "6.4.2"
+ # Make sure this is in sync with build-cache.yml
+ HIPSDK_INSTALLER_VERSION: "25.Q3"
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Grab rocWMMA package
+ id: grab_rocwmma
+ run: |
+ curl -o rocwmma.deb "https://repo.radeon.com/rocm/apt/${{ env.ROCM_VERSION }}/pool/main/r/rocwmma-dev/rocwmma-dev_1.7.0.60402-120~24.04_amd64.deb"
+ 7z x rocwmma.deb
+ 7z x data.tar
+
+ - name: Use ROCm Installation Cache
+ uses: actions/cache@v5
+ id: cache-rocm
+ with:
+ path: C:\Program Files\AMD\ROCm
+ key: rocm-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ runner.os }}
+
+ - name: Setup ROCm
+ if: steps.cache-rocm.outputs.cache-hit != 'true'
+ uses: ./.github/actions/windows-setup-rocm
+ with:
+ version: ${{ env.HIPSDK_INSTALLER_VERSION }}
+
+ - name: Verify ROCm
+ id: verify
+ run: |
+ # Find and test ROCm installation
+ $clangPath = Get-ChildItem 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | Select-Object -First 1
+ if (-not $clangPath) {
+ Write-Error "ROCm installation not found"
+ exit 1
+ }
+ & $clangPath.FullName --version
+
+ - name: Install ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ${{ github.job }}
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Build
+ id: cmake_build
+ 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('\', '/'))/opt/rocm-${{ env.ROCM_VERSION }}/include/" `
+ -DCMAKE_BUILD_TYPE=Release `
+ -DLLAMA_BUILD_BORINGSSL=ON `
+ -DROCM_DIR="${env:HIP_PATH}" `
+ -DGGML_HIP=ON `
+ -DGGML_HIP_ROCWMMA_FATTN=ON `
+ -DGGML_RPC=ON
+ cmake --build build -j ${env:NUMBER_OF_PROCESSORS}
+
+ ios-xcode-build:
+ runs-on: macos-latest
+
+ steps:
+ - name: Checkout code
+ uses: actions/checkout@v6
+
+ - name: Setup Xcode
+ uses: maxim-lobanov/setup-xcode@v1
+ with:
+ xcode-version: latest-stable
+
+ - name: Build
+ id: cmake_build
+ run: |
+ sysctl -a
+ cmake -B build -G Xcode \
+ -DGGML_METAL_USE_BF16=ON \
+ -DGGML_METAL_EMBED_LIBRARY=ON \
+ -DLLAMA_OPENSSL=OFF \
+ -DLLAMA_BUILD_EXAMPLES=OFF \
+ -DLLAMA_BUILD_TOOLS=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 $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
+
+ - name: xcodebuild for swift package
+ id: xcodebuild
+ run: |
+ ./build-xcframework.sh
+
+ - name: Upload xcframework artifact
+ uses: actions/upload-artifact@v6
+ with:
+ name: llama-xcframework
+ path: build-apple/llama.xcframework/
+ retention-days: 1
+
+ - name: Build Xcode project
+ run: |
+ xcodebuild -downloadPlatform iOS
+ xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build
+
+ android-build:
+ runs-on: ubuntu-latest
+
+ steps:
+ - name: Clone
+ uses: actions/checkout@v6
+
+ # Disabled due to size (400MB) and always 0 cache hits
+ # - name: ccache
+ # uses: ggml-org/ccache-action@v1.2.16
+ # with:
+ # key: android-build
+ # evict-old-files: 1d
+
+ - name: Set up JDK
+ uses: actions/setup-java@v5
+ with:
+ java-version: 17
+ distribution: zulu
+
+ - name: Setup Android SDK
+ uses: android-actions/setup-android@v3
+ with:
+ log-accepted-android-sdk-licenses: false
+
+ - name: Build
+ run: |
+ cd examples/llama.android
+ ./gradlew build --no-daemon
+
+ android-ndk-build:
+ runs-on: ubuntu-latest
+
+ env:
+ OPENCL_VERSION: 2025.07.22
+
+ strategy:
+ matrix:
+ include:
+ - build: 'arm64-cpu'
+ defines: '-D ANDROID_ABI=arm64-v8a -D ANDROID_PLATFORM=android-31 -D CMAKE_TOOLCHAIN_FILE=${ANDROID_NDK_ROOT}/build/cmake/android.toolchain.cmake -D GGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv8.5-a+fp16+i8mm -G Ninja -D LLAMA_OPENSSL=OFF -D GGML_OPENMP=OFF'
+ - build: 'arm64-snapdragon'
+ defines: '--preset arm64-android-snapdragon-release'
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Install OpenCL Headers and Libs
+ id: install_opencl
+ if: ${{ matrix.build == 'arm64-snapdragon' }}
+ run: |
+ mkdir opencl
+ curl -L -o opencl/clhpp.tar.gz https://github.com/KhronosGroup/OpenCL-CLHPP/archive/refs/tags/v${OPENCL_VERSION}.tar.gz
+ curl -L -o opencl/headers.tar.gz https://github.com/KhronosGroup/OpenCL-Headers/archive/refs/tags/v${OPENCL_VERSION}.tar.gz
+ curl -L -o opencl/icd-loader.tar.gz https://github.com/KhronosGroup/OpenCL-ICD-Loader/archive/refs/tags/v${OPENCL_VERSION}.tar.gz
+ tar -xaf opencl/headers.tar.gz -C opencl
+ tar -xaf opencl/clhpp.tar.gz -C opencl
+ tar -xaf opencl/icd-loader.tar.gz -C opencl
+ sudo cp -r opencl/OpenCL-Headers-${OPENCL_VERSION}/CL ${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include
+ sudo cp -r opencl/OpenCL-CLHPP-${OPENCL_VERSION}/include/CL/* ${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include/CL
+ cd opencl/OpenCL-ICD-Loader-${OPENCL_VERSION}
+ cmake -B build -G Ninja -DCMAKE_BUILD_TYPE=Release -DCMAKE_TOOLCHAIN_FILE=${ANDROID_NDK_ROOT}/build/cmake/android.toolchain.cmake -DOPENCL_ICD_LOADER_HEADERS_DIR=${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include -DANDROID_ABI=arm64-v8a -DANDROID_PLATFORM=31 -DANDROID_STL=c++_shared
+ cmake --build build
+ sudo cp build/libOpenCL.so ${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/lib/aarch64-linux-android
+ rm -rf opencl
+
+ - name: Install Hexagon SDK
+ id: install_hexsdk
+ if: ${{ matrix.build == 'arm64-snapdragon' }}
+ env:
+ HEXSDK_VER: 6.4.0.2
+ HEXTLS_VER: 19.0.04
+ run: |
+ curl -L -o hex-sdk.tar.gz https://github.com/snapdragon-toolchain/hexagon-sdk/releases/download/v$HEXSDK_VER/hexagon-sdk-v$HEXSDK_VER-amd64-lnx.tar.xz
+ mkdir hex-sdk
+ tar -xaf hex-sdk.tar.gz -C hex-sdk
+ ls -l hex-sdk
+ sudo mv hex-sdk /opt/hexagon
+ echo "HEXAGON_SDK_ROOT=/opt/hexagon/$HEXSDK_VER" >> "$GITHUB_ENV"
+ echo "HEXAGON_TOOLS_ROOT=/opt/hexagon/$HEXSDK_VER/tools/HEXAGON_Tools/$HEXTLS_VER" >> "$GITHUB_ENV"
+ echo "DEFAULT_HLOS_ARCH=64" >> "$GITHUB_ENV"
+ echo "DEFAULT_TOOLS_VARIANT=toolv19" >> "$GITHUB_ENV"
+ echo "DEFAULT_NO_QURT_INC=0" >> "$GITHUB_ENV"
+ echo "DEFAULT_DSP_ARCH=v73" >> "$GITHUB_ENV"
+
+ - name: Update CMake presets
+ id: update_presets
+ if: ${{ matrix.build == 'arm64-snapdragon' }}
+ run: |
+ cp docs/backend/snapdragon/CMakeUserPresets.json .
+
+ - name: Build
+ id: ndk_build
+ run: |
+ cmake ${{ matrix.defines }} -B build
+ cmake --build build
+ cmake --install build --prefix pkg-adb/llama.cpp
+
+ - name: Test
+ id: cmake_test
+ run: |
+ echo "FIXME: test on devices"
+
+ openEuler-latest-cmake-cann:
+ defaults:
+ run:
+ shell: bash -el {0}
+ strategy:
+ matrix:
+ arch: [x86, aarch64]
+ chip_type: ['910b', '310p']
+ build: ['Release']
+ use_acl_graph: ['on', 'off']
+ exclude:
+ # 310P does not support USE_ACL_GRAPH=on
+ - chip_type: '310p'
+ use_acl_graph: 'on'
+ runs-on: ${{ matrix.arch == 'aarch64' && 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
+ steps:
+ - name: Checkout
+ uses: actions/checkout@v6
+ with:
+ fetch-depth: 0
+
+ - name: Free up disk space
+ uses: ggml-org/free-disk-space@v1.3.1
+ with:
+ tool-cache: true
+
+ - name: Set container image
+ id: cann-image
+ run: |
+ image="ascendai/cann:${{ matrix.chip_type == '910b' && '8.3.rc2-910b-openeuler24.03-py3.11' || '8.3.rc2-310p-openeuler24.03-py3.11' }}"
+ echo "image=${image}" >> "${GITHUB_OUTPUT}"
+
+ - name: Pull container image
+ run: docker pull "${{ steps.cann-image.outputs.image }}"
+
+ - name: Build
+ env:
+ BUILD_TYPE: ${{ matrix.build }}
+ SOC_TYPE: ascend${{ matrix.chip_type }}
+ USE_ACL_GRAPH: ${{ matrix.use_acl_graph }}
+ run: |
+ HOST_UID=$(id -u)
+ HOST_GID=$(id -g)
+
+ docker run --rm \
+ -v "${PWD}:/workspace" \
+ -w /workspace \
+ -e SOC_TYPE=${SOC_TYPE} \
+ -e BUILD_TYPE=${BUILD_TYPE} \
+ -e USE_ACL_GRAPH=${USE_ACL_GRAPH} \
+ "${{ steps.cann-image.outputs.image }}" \
+ bash -lc '
+ set -e
+ yum install -y --setopt=install_weak_deps=False --setopt=tsflags=nodocs git gcc gcc-c++ make cmake openssl-devel
+ yum clean all && rm -rf /var/cache/yum
+ git config --global --add safe.directory "/workspace"
+ 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=${BUILD_TYPE} \
+ -DGGML_CANN=on \
+ -DSOC_TYPE=${SOC_TYPE} \
+ -DUSE_ACL_GRAPH=${USE_ACL_GRAPH}
+ cmake --build build -j $(nproc)
+
+ chown -R '"${HOST_UID}"':'"${HOST_GID}"' /workspace/build
+ '
+
+# TODO: simplify the following workflows using a matrix
+# TODO: run lighter CI on PRs and the full CI only on master (if needed)
+ ggml-ci-x64-cpu-low-perf:
+ runs-on: ubuntu-22.04
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ggml-ci-x64-cpu-low-perf
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Dependencies
+ id: depends
+ run: |
+ sudo apt-get update
+ sudo apt-get install build-essential
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
+
+ ggml-ci-arm64-cpu-low-perf:
+ runs-on: ubuntu-22.04-arm
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ggml-ci-arm64-cpu-low-perf
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Dependencies
+ id: depends
+ run: |
+ sudo apt-get update
+ sudo apt-get install build-essential
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
+
+ ggml-ci-x64-cpu-high-perf:
+ runs-on: ubuntu-22.04
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ggml-ci-x64-cpu-high-perf
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Dependencies
+ id: depends
+ run: |
+ sudo apt-get update
+ sudo apt-get install build-essential
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
+
+ ggml-ci-arm64-cpu-high-perf:
+ runs-on: ubuntu-22.04-arm
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ggml-ci-arm64-cpu-high-perf
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Dependencies
+ id: depends
+ run: |
+ sudo apt-get update
+ sudo apt-get install build-essential
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_NO_SVE=1 GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
+
+ ggml-ci-arm64-cpu-high-perf-sve:
+ runs-on: ubuntu-22.04-arm
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ggml-ci-arm64-cpu-high-perf-sve
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Dependencies
+ id: depends
+ run: |
+ sudo apt-get update
+ sudo apt-get install build-essential
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ LLAMA_ARG_THREADS=$(nproc) GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
+
+ ggml-ci-x64-nvidia-cuda:
+ runs-on: [self-hosted, Linux, X64, NVIDIA]
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ nvidia-smi
+ GG_BUILD_CUDA=1 bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
+
+ ggml-ci-x64-nvidia-vulkan-cm:
+ runs-on: [self-hosted, Linux, X64, NVIDIA]
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ vulkaninfo --summary
+ GG_BUILD_VULKAN=1 GGML_VK_DISABLE_COOPMAT2=1 bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
+
+ ggml-ci-x64-nvidia-vulkan-cm2:
+ runs-on: [self-hosted, Linux, X64, NVIDIA, COOPMAT2]
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ vulkaninfo --summary
+ GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
+
+ ggml-ci-x64-cpu-amx:
+ runs-on: [self-hosted, Linux, X64, CPU, AMX]
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
+
+ # ggml-ci-x64-amd-vulkan:
+ # runs-on: [self-hosted, Linux, X64, AMD]
+
+ # steps:
+ # - name: Clone
+ # id: checkout
+ # uses: actions/checkout@v6
+
+ # - name: Test
+ # id: ggml-ci
+ # run: |
+ # vulkaninfo --summary
+ # GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
+
+ # ggml-ci-x64-amd-rocm:
+ # runs-on: [self-hosted, Linux, X64, AMD]
+
+ # steps:
+ # - name: Clone
+ # id: checkout
+ # uses: actions/checkout@v6
+
+ # - name: Test
+ # id: ggml-ci
+ # run: |
+ # amd-smi static
+ # GG_BUILD_ROCM=1 GG_BUILD_AMDGPU_TARGETS="gfx1101" bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
+
+ ggml-ci-mac-metal:
+ runs-on: [self-hosted, macOS, ARM64]
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ GG_BUILD_METAL=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
+
+ ggml-ci-mac-webgpu:
+ runs-on: [self-hosted, macOS, ARM64]
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Dawn Dependency
+ id: dawn-depends
+ run: |
+ DAWN_VERSION="v2.0.0"
+ DAWN_OWNER="reeselevine"
+ DAWN_REPO="dawn"
+ DAWN_ASSET_NAME="Dawn-5e9a4865b1635796ccc77dd30057f2b4002a1355-macos-latest-Release"
+ echo "Fetching release asset from https://github.com/${DAWN_OWNER}/${DAWN_REPO}/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.zip"
+ curl -L -o artifact.zip \
+ "https://github.com/${DAWN_OWNER}/${DAWN_REPO}/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.zip"
+ mkdir dawn
+ unzip artifact.zip
+ tar -xvf ${DAWN_ASSET_NAME}.tar.gz -C dawn --strip-components=1
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ GG_BUILD_WEBGPU=1 GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \
+ bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
+
+ ggml-ci-mac-vulkan:
+ runs-on: [self-hosted, macOS, ARM64]
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ vulkaninfo --summary
+ GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
+
+ ggml-ci-arm64-cpu-kleidiai:
+ runs-on: ubuntu-22.04-arm
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ggml-ci-arm64-cpu-kleidiai
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Dependencies
+ id: depends
+ run: |
+ sudo apt-get update
+ sudo apt-get install -y build-essential
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ GG_BUILD_KLEIDIAI=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
+
+ ubuntu-cpu-cmake-riscv64-native:
+ runs-on: RISCV64
+
+ steps:
+ - name: Install dependencies
+ run: |
+ sudo apt-get update
+
+ # Install necessary packages
+ sudo apt-get install -y libatomic1 libtsan2 gcc-14 g++-14 rustup cmake build-essential libssl-dev wget ccache git-lfs
+
+ # Set gcc-14 and g++-14 as the default compilers
+ sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100
+ sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100
+ sudo ln -sf /usr/bin/gcc-14 /usr/bin/gcc
+ sudo ln -sf /usr/bin/g++-14 /usr/bin/g++
+
+ # Install Rust stable version
+ rustup install stable
+ rustup default stable
+
+ git lfs install
+
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Check environment
+ run: |
+ uname -a
+ gcc --version
+ g++ --version
+ ldd --version
+ cmake --version
+ rustc --version
+
+ - name: Setup ccache
+ run: |
+ # Set unique cache directory for this job
+ export CCACHE_DIR="$HOME/.ccache/cpu-cmake-rv64-native"
+ mkdir -p "$CCACHE_DIR"
+
+ # Configure ccache for optimal performance
+ ccache --set-config=max_size=5G
+ ccache --set-config=compression=true
+ ccache --set-config=compression_level=6
+ ccache --set-config=cache_dir="$CCACHE_DIR"
+
+ # Enable more aggressive caching
+ ccache --set-config=sloppiness=file_macro,time_macros,include_file_mtime,include_file_ctime
+ ccache --set-config=hash_dir=false
+
+ # Export for subsequent steps
+ echo "CCACHE_DIR=$CCACHE_DIR" >> $GITHUB_ENV
+ echo "PATH=/usr/lib/ccache:$PATH" >> $GITHUB_ENV
+
+ - name: Build
+ id: cmake_build
+ run: |
+ cmake -B build \
+ -DCMAKE_BUILD_TYPE=Release \
+ -DGGML_OPENMP=OFF \
+ -DLLAMA_BUILD_EXAMPLES=ON \
+ -DLLAMA_BUILD_TOOLS=ON \
+ -DLLAMA_BUILD_TESTS=ON \
+ -DCMAKE_C_COMPILER_LAUNCHER=ccache \
+ -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
+ -DGGML_RPC=ON \
+ -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
+ -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
+
+ cmake --build build --config Release -j $(nproc)
+
+ - name: Test
+ id: cmake_test
+ run: |
+ cd build
+ ctest -L main --verbose --timeout 900
+
+ - name: Test llama2c conversion
+ id: llama2c_test
+ run: |
+ cd build
+ echo "Fetch tokenizer"
+ wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin
+ echo "Fetch llama2c model"
+ wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin
+ ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf
+ ./bin/llama-completion -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
+
+ ubuntu-cmake-sanitizer-riscv64-native:
+ runs-on: RISCV64
+
+ continue-on-error: true
+
+ strategy:
+ matrix:
+ sanitizer: [ADDRESS, THREAD, UNDEFINED]
+ build_type: [Debug]
+
+ steps:
+ - name: Install dependencies
+ run: |
+ sudo apt-get update
+
+ # Install necessary packages
+ sudo apt-get install -y libatomic1 libtsan2 gcc-14 g++-14 rustup cmake build-essential wget ccache git-lfs
+
+ # Set gcc-14 and g++-14 as the default compilers
+ sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100
+ sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100
+ sudo ln -sf /usr/bin/gcc-14 /usr/bin/gcc
+ sudo ln -sf /usr/bin/g++-14 /usr/bin/g++
+
+ # Install Rust stable version
+ rustup install stable
+ rustup default stable
+
+ git lfs install
+
+ - name: GCC version check
+ run: |
+ gcc --version
+ g++ --version
+
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Setup ccache
+ run: |
+ # Unique cache directory per matrix combination
+ export CCACHE_DIR="$HOME/.ccache/sanitizer-${{ matrix.sanitizer }}-${{ matrix.build_type }}"
+ mkdir -p "$CCACHE_DIR"
+
+ # Configure ccache
+ ccache --set-config=max_size=5G
+ ccache --set-config=compression=true
+ ccache --set-config=compression_level=6
+ ccache --set-config=cache_dir="$CCACHE_DIR"
+ ccache --set-config=sloppiness=file_macro,time_macros,include_file_mtime,include_file_ctime
+ ccache --set-config=hash_dir=false
+
+ # Export for subsequent steps
+ echo "CCACHE_DIR=$CCACHE_DIR" >> $GITHUB_ENV
+ echo "PATH=/usr/lib/ccache:$PATH" >> $GITHUB_ENV
+
+ - name: Build
+ id: cmake_build
+ if: ${{ matrix.sanitizer != 'THREAD' }}
+ run: |
+ cmake -B build \
+ -DLLAMA_OPENSSL=OFF \
+ -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
+ -DGGML_OPENMP=ON \
+ -DLLAMA_BUILD_EXAMPLES=ON \
+ -DLLAMA_BUILD_TOOLS=ON \
+ -DLLAMA_BUILD_TESTS=OFF \
+ -DCMAKE_C_COMPILER_LAUNCHER=ccache \
+ -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
+ -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
+ -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
+ -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
+
+ cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
+
+ - name: Build (no OpenMP)
+ id: cmake_build_no_openmp
+ if: ${{ matrix.sanitizer == 'THREAD' }}
+ run: |
+ cmake -B build \
+ -DLLAMA_OPENSSL=OFF \
+ -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
+ -DGGML_OPENMP=OFF \
+ -DLLAMA_BUILD_EXAMPLES=ON \
+ -DLLAMA_BUILD_TOOLS=ON \
+ -DLLAMA_BUILD_TESTS=OFF \
+ -DCMAKE_C_COMPILER_LAUNCHER=ccache \
+ -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
+ -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
+ -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
+ -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
+
+ cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
+
+ - name: Test
+ id: cmake_test
+ run: |
+ cd build
+ ctest -L main --verbose --timeout 900
+
+
+ ubuntu-llguidance-riscv64-native:
+ runs-on: RISCV64
+ steps:
+ - name: Install dependencies
+ run: |
+ sudo apt-get update
+
+ # Install necessary packages
+ sudo apt-get install -y libatomic1 libtsan2 gcc-14 g++-14 rustup cmake build-essential wget ccache git-lfs
+
+ # Set gcc-14 and g++-14 as the default compilers
+ sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100
+ sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100
+ sudo ln -sf /usr/bin/gcc-14 /usr/bin/gcc
+ sudo ln -sf /usr/bin/g++-14 /usr/bin/g++
+
+ # Install Rust stable version
+ rustup install stable
+ rustup default stable
+
+ git lfs install
+
+ - name: GCC version check
+ run: |
+ gcc --version
+ g++ --version
+
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Setup ccache
+ run: |
+ export CCACHE_DIR="$HOME/.ccache/llguidance-riscv64"
+ mkdir -p "$CCACHE_DIR"
+
+ ccache --set-config=max_size=5G
+ ccache --set-config=compression=true
+ ccache --set-config=compression_level=6
+ ccache --set-config=cache_dir="$CCACHE_DIR"
+ ccache --set-config=sloppiness=file_macro,time_macros,include_file_mtime,include_file_ctime
+ ccache --set-config=hash_dir=false
+
+ echo "CCACHE_DIR=$CCACHE_DIR" >> $GITHUB_ENV
+ echo "PATH=/usr/lib/ccache:$PATH" >> $GITHUB_ENV
+
+ - name: Build
+ id: cmake_build
+ run: |
+ cmake -B build \
+ -DLLAMA_OPENSSL=OFF \
+ -DCMAKE_BUILD_TYPE=Release \
+ -DGGML_OPENMP=OFF \
+ -DLLAMA_BUILD_EXAMPLES=ON \
+ -DLLAMA_BUILD_TOOLS=ON \
+ -DLLAMA_BUILD_TESTS=OFF \
+ -DCMAKE_C_COMPILER_LAUNCHER=ccache \
+ -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
+ -DLLAMA_LLGUIDANCE=ON \
+ -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
+ -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
+
+ cmake --build build --config Release -j $(nproc)
+
+ - name: Test
+ id: cmake_test
+ run: |
+ cd build
+ ctest -L main --verbose --timeout 900
+
+
+ ubuntu-cmake-rpc-riscv64-native:
+ runs-on: RISCV64
+
+ continue-on-error: true
+
+ steps:
+ - name: Install dependencies
+ run: |
+ sudo apt-get update
+
+ # Install necessary packages
+ sudo apt-get install -y libatomic1 libtsan2 gcc-14 g++-14 rustup cmake build-essential libssl-dev wget ccache git-lfs
+
+ # Set gcc-14 and g++-14 as the default compilers
+ sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100
+ sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100
+ sudo ln -sf /usr/bin/gcc-14 /usr/bin/gcc
+ sudo ln -sf /usr/bin/g++-14 /usr/bin/g++
+
+ # Install Rust stable version
+ rustup install stable
+ rustup default stable
+
+ git lfs install
+
+ - name: GCC version check
+ run: |
+ gcc --version
+ g++ --version
+
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Setup ccache
+ run: |
+ export CCACHE_DIR="$HOME/.ccache/rpc-riscv64"
+ mkdir -p "$CCACHE_DIR"
+
+ ccache --set-config=max_size=5G
+ ccache --set-config=compression=true
+ ccache --set-config=compression_level=6
+ ccache --set-config=cache_dir="$CCACHE_DIR"
+ ccache --set-config=sloppiness=file_macro,time_macros,include_file_mtime,include_file_ctime
+ ccache --set-config=hash_dir=false
+
+ echo "CCACHE_DIR=$CCACHE_DIR" >> $GITHUB_ENV
+ echo "PATH=/usr/lib/ccache:$PATH" >> $GITHUB_ENV
+
+ - name: Build
+ id: cmake_build
+ run: |
+ cmake -B build \
+ -DCMAKE_BUILD_TYPE=Release \
+ -DGGML_OPENMP=OFF \
+ -DLLAMA_BUILD_EXAMPLES=ON \
+ -DLLAMA_BUILD_TOOLS=ON \
+ -DLLAMA_BUILD_TESTS=ON \
+ -DCMAKE_C_COMPILER_LAUNCHER=ccache \
+ -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
+ -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
+ -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14 \
+ -DGGML_RPC=ON
+
+ cmake --build build --config Release -j $(nproc)
+
+ - name: Test
+ id: cmake_test
+ run: |
+ cd build
+ ctest -L main --verbose
+
+ ggml-ci-arm64-graviton4-kleidiai:
+ runs-on: ah-ubuntu_22_04-c8g_8x
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Dependencies
+ id: depends
+ run: |
+ set -euxo pipefail
+ sudo apt-get update
+ sudo DEBIAN_FRONTEND=noninteractive NEEDRESTART_MODE=a \
+ apt-get install -y \
+ build-essential \
+ python3-venv \
+ gpg \
+ wget \
+ time \
+ git-lfs
+
+ git lfs install
+
+ # install the latest cmake
+ sudo install -d /usr/share/keyrings
+ wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc \
+ | gpg --dearmor \
+ | sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null
+ echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ jammy main' \
+ | sudo tee /etc/apt/sources.list.d/kitware.list
+ sudo apt-get update
+ sudo apt-get install -y cmake
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.16
+ with:
+ key: ggml-ci-arm64-graviton4-kleidiai
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ GG_BUILD_KLEIDIAI=1 \
+ GG_BUILD_EXTRA_TESTS_0=1 \
+ bash ./ci/run.sh ./tmp/results ./tmp/mnt
generated by cgit v1.2.3 (git 2.46.0) at 2026-04-29 13:27:47 +0000