]
env:
+ GH_TOKEN: ${{ github.token }}
BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
CMAKE_ARGS: "-DLLAMA_BUILD_EXAMPLES=OFF -DLLAMA_BUILD_TESTS=OFF -DLLAMA_BUILD_TOOLS=ON -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON"
runs-on: ${{ matrix.os }}
+ permissions:
+ actions: write
+
steps:
- name: Clone
id: checkout
uses: ggml-org/ccache-action@v1.2.21
with:
key: release-${{ matrix.os }}-${{ matrix.arch }}
- append-timestamp: false # note: use this only with non-concurrent jobs!
- name: Build
id: cmake_build
${{ env.CMAKE_ARGS }}
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
+ - name: ccache-clear
+ uses: ./.github/actions/ccache-clear
+ with:
+ key: release-${{ matrix.os }}-${{ matrix.arch }}
+
- name: Determine tag name
id: tag
uses: ./.github/actions/get-tag-name
runs-on: ${{ matrix.os }}
+ permissions:
+ actions: write
+
steps:
- name: Clone
id: checkout
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- - name: ccache
- if: ${{ matrix.build != 's390x' }}
- uses: ggml-org/ccache-action@v1.2.21
- with:
- key: release-${{ matrix.os }}-cpu
- append-timestamp: false # note: use this only with non-concurrent jobs!
-
- name: Dependencies
id: depends
run: |
echo "CC=gcc-14" >> "$GITHUB_ENV"
echo "CXX=g++-14" >> "$GITHUB_ENV"
+ - name: ccache
+ if: ${{ matrix.build != 's390x' }}
+ uses: ggml-org/ccache-action@v1.2.21
+ with:
+ key: release-${{ matrix.os }}-cpu
+
- name: Build
id: cmake_build
run: |
${{ env.CMAKE_ARGS }}
cmake --build build --config Release -j $(nproc)
+ - name: ccache-clear
+ uses: ./.github/actions/ccache-clear
+ with:
+ key: release-${{ matrix.os }}-cpu
+
- name: Determine tag name
id: tag
uses: ./.github/actions/get-tag-name
runs-on: ${{ matrix.os }}
+ permissions:
+ actions: write
+
steps:
- name: Clone
id: checkout
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- - name: ccache
- uses: ggml-org/ccache-action@v1.2.21
- with:
- key: release-${{ matrix.os }}-vulkan
- append-timestamp: false # note: use this only with non-concurrent jobs!
-
- name: Dependencies
id: depends
run: |
echo "CXX=g++-14" >> "$GITHUB_ENV"
fi
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.21
+ with:
+ key: release-${{ matrix.os }}-vulkan
+
- name: Build
id: cmake_build
run: |
${{ env.CMAKE_ARGS }}
cmake --build build --config Release -j $(nproc)
+ - name: ccache-clear
+ uses: ./.github/actions/ccache-clear
+ with:
+ key: release-${{ matrix.os }}-vulkan
+
- name: Determine tag name
id: tag
uses: ./.github/actions/get-tag-name
runs-on: ubuntu-latest
+ #permissions:
+ # actions: write
+
env:
NDK_VERSION: "29.0.14206865"
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- # note : disabled to spare some cache space (https://github.com/ggml-org/llama.cpp/pull/23789)
- # for some reason, the ccache does not improve the build time in this case
- # example:
- # cache off: https://github.com/ggerganov/tmp2/actions/runs/26534713799/job/78160400831
- # cache on: https://github.com/ggerganov/tmp2/actions/runs/26534713799/job/78224189394
- #
- #- name: ccache
- # uses: ggml-org/ccache-action@v1.2.21
- # with:
- # key: release-android-arm64
- # append-timestamp: false # note: use this only with non-concurrent jobs!
-
- name: Set up JDK
uses: actions/setup-java@v5
with:
sdkmanager "ndk;${{ env.NDK_VERSION }}"
echo "ANDROID_NDK=${ANDROID_SDK_ROOT}/ndk/${{ env.NDK_VERSION }}" >> $GITHUB_ENV
+ # note : disabled to spare some cache space (https://github.com/ggml-org/llama.cpp/pull/23789)
+ # for some reason, the ccache does not improve the build time in this case
+ # example:
+ # cache off: https://github.com/ggerganov/tmp2/actions/runs/26534713799/job/78160400831
+ # cache on: https://github.com/ggerganov/tmp2/actions/runs/26534713799/job/78224189394
+ #
+ #- name: ccache
+ # uses: ggml-org/ccache-action@v1.2.21
+ # with:
+ # key: release-android-arm64
+
- name: Build
id: cmake_build
run: |
${{ env.CMAKE_ARGS }}
cmake --build build --config Release -j $(nproc)
+ #- name: ccache-clear
+ # uses: ./.github/actions/ccache-clear
+ # with:
+ # key: release-android-arm64
+
- name: Determine tag name
id: tag
uses: ./.github/actions/get-tag-name
runs-on: ubuntu-24.04
+ permissions:
+ actions: write
+
outputs:
openvino_version: ${{ steps.openvino_version.outputs.value }}
uses: ggml-org/ccache-action@v1.2.21
with:
key: release-ubuntu-24.04-openvino-release-no-preset-v1
- append-timestamp: false # note: use this only with non-concurrent jobs!
- name: Dependencies
run: |
-DGGML_OPENVINO=ON
cmake --build build/ReleaseOV --config Release -j $(nproc)
+ - name: ccache-clear
+ uses: ./.github/actions/ccache-clear
+ with:
+ key: release-ubuntu-24.04-openvino-release-no-preset-v1
+
- name: Determine tag name
id: tag
uses: ./.github/actions/get-tag-name
runs-on: windows-2025
+ permissions:
+ actions: write
+
strategy:
matrix:
include:
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
+ - name: Install Ninja
+ run: |
+ choco install ninja
+
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: release-windows-2025-${{ matrix.arch }}-cpu
- append-timestamp: false # note: use this only with non-concurrent jobs!
-
- - name: Install Ninja
- run: |
- choco install ninja
- name: Build
shell: cmd
${{ env.CMAKE_ARGS }}
cmake --build build --config Release
+ - name: ccache-clear
+ uses: ./.github/actions/ccache-clear
+ with:
+ key: release-windows-2025-${{ matrix.arch }}-cpu
+
- name: Pack artifacts
id: pack_artifacts
run: |
runs-on: windows-2025
+ permissions:
+ actions: write
+
env:
OPENBLAS_VERSION: 0.3.23
VULKAN_VERSION: 1.4.313.2
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- - name: ccache
- uses: ggml-org/ccache-action@v1.2.21
- with:
- key: release-windows-2025-${{ matrix.arch }}-${{ matrix.backend }}
- append-timestamp: false # note: use this only with non-concurrent jobs!
-
- name: Install Vulkan SDK
id: get_vulkan
if: ${{ matrix.backend == 'vulkan' }}
run: |
choco install ninja
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.21
+ with:
+ key: release-windows-2025-${{ matrix.arch }}-${{ matrix.backend }}
+
- name: Install OpenCL Headers and Libs
id: install_opencl
if: ${{ matrix.backend == 'opencl-adreno' && matrix.arch == 'arm64' }}
cmake -S . -B build ${{ matrix.defines }} -DGGML_NATIVE=OFF -DGGML_CPU=OFF -DGGML_BACKEND_DL=ON -DLLAMA_BUILD_BORINGSSL=ON
cmake --build build --config Release --target ${{ matrix.target }}
+ - name: ccache-clear
+ uses: ./.github/actions/ccache-clear
+ with:
+ key: release-windows-2025-${{ matrix.arch }}-${{ matrix.backend }}
+
- name: Pack artifacts
id: pack_artifacts
run: |
runs-on: windows-2022
+ permissions:
+ actions: write
+
strategy:
matrix:
cuda: ['12.4', '13.3']
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- - name: ccache
- uses: ggml-org/ccache-action@v1.2.21
- with:
- key: release-windows-2022-x64-cuda-${{ matrix.cuda }}
- append-timestamp: false # note: use this only with non-concurrent jobs!
-
- name: Install Cuda Toolkit
uses: ./.github/actions/windows-setup-cuda
with:
run: |
choco install ninja
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.21
+ with:
+ key: release-windows-2022-x64-cuda-${{ matrix.cuda }}
+
- name: Build
id: cmake_build
shell: cmd
set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
cmake --build build --config Release -j %NINJA_JOBS% --target ggml-cuda
+ - name: ccache-clear
+ uses: ./.github/actions/ccache-clear
+ with:
+ key: release-windows-2022-x64-cuda-${{ matrix.cuda }}
+
- name: Pack artifacts
id: pack_artifacts
run: |
# uses: ggml-org/ccache-action@v1.2.21
# with:
# key: release-windows-2022-x64-sycl
-# append-timestamp: false # note: use this only with non-concurrent jobs!
#
# - name: Build
# id: cmake_build
# uses: ggml-org/ccache-action@v1.2.21
# with:
# key: release-ubuntu-24.04-sycl
-# append-timestamp: false # note: use this only with non-concurrent jobs!
#
# - name: Build
# id: cmake_build
runs-on: ubuntu-22.04
+ permissions:
+ actions: write
+
strategy:
matrix:
include:
uses: ggml-org/ccache-action@v1.2.21
with:
key: release-ubuntu-22.04-rocm-${{ matrix.ROCM_VERSION }}
- append-timestamp: false # note: use this only with non-concurrent jobs!
- name: Dependencies
id: depends
${{ env.CMAKE_ARGS }}
cmake --build build --config Release -j $(nproc)
+ - name: ccache-clear
+ uses: ./.github/actions/ccache-clear
+ with:
+ key: release-ubuntu-22.04-rocm-${{ matrix.ROCM_VERSION }}
+
- name: Determine tag name
id: tag
uses: ./.github/actions/get-tag-name
runs-on: windows-2022
+ permissions:
+ actions: write
+
env:
HIPSDK_INSTALLER_VERSION: "26.Q1"
uses: ggml-org/ccache-action@v1.2.21
with:
key: release-windows-2022-x64-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}
- append-timestamp: false # note: use this only with non-concurrent jobs!
- name: Install ROCm
if: steps.cache-rocm.outputs.cache-hit != 'true'
cp "${env:HIP_PATH}\bin\rocblas\library\*" "build\bin\rocblas\library\"
cp "${env:HIP_PATH}\bin\hipblaslt\library\*" "build\bin\hipblaslt\library\"
+ - name: ccache-clear
+ uses: ./.github/actions/ccache-clear
+ with:
+ key: release-windows-2022-x64-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}
+
- name: Pack artifacts
id: pack_artifacts
run: |
ios-xcode-build:
needs: [check_release]
if: ${{ needs.check_release.outputs.should_release == 'true' }}
- runs-on: macos-26
+ # TODO: figure out how to make this work with macos-26
+ # https://github.com/ggml-org/llama.cpp/actions/runs/26652714555/job/78604869474
+ runs-on: macos-15
steps:
- name: Checkout code
overview / pkg / ggml / sources / llama.cpp / commitdiff