feat: first commit #23
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: ci | |
| permissions: | |
| contents: read | |
| pull-requests: read | |
| actions: read | |
| env: | |
| VERSION: "${{ github.ref_name }}" | |
| on: | |
| workflow_dispatch: { } | |
| push: | |
| tags: | |
| - "v*.*.*" | |
| branches: | |
| - main | |
| paths-ignore: | |
| - "docs/**" | |
| - "**.md" | |
| - "**.mdx" | |
| - "**.png" | |
| - "**.jpg" | |
| pull_request: | |
| branches: | |
| - main | |
| paths-ignore: | |
| - "docs/**" | |
| - "**.md" | |
| - "**.mdx" | |
| - "**.png" | |
| - "**.jpg" | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} | |
| cancel-in-progress: true | |
| jobs: | |
| darwin-metal: | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| arch: [ amd64, arm64 ] | |
| # see https://github.com/actions/runner-images?tab=readme-ov-file#available-images, | |
| # https://support.apple.com/en-us/102894. | |
| runs-on: ${{ matrix.arch == 'amd64' && 'macos-13' || 'macos-14' }} | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 | |
| submodules: 'recursive' | |
| - name: Setup XCode | |
| uses: maxim-lobanov/setup-xcode@v1 | |
| with: | |
| xcode-version: '15.2' | |
| - name: Setup Cache | |
| timeout-minutes: 5 | |
| uses: actions/cache@v3 | |
| with: | |
| key: cache-darwin-metal-${{ matrix.arch }}-${{ hashFiles('**/.gitmodules') }} | |
| path: | | |
| ${{ github.workspace }}/.cache | |
| - name: Deps | |
| continue-on-error: true | |
| run: | | |
| brew update && brew install ccache | |
| - name: Build | |
| run: | | |
| echo "===== BUILD =====" | |
| mkdir -p ${{ github.workspace }}/.cache | |
| CCACHE_DIR=${{ github.workspace }}/.cache/ccache make -j LLAMA_METAL=1 | |
| echo "===== RESULT =====" | |
| [ -f ${{ github.workspace }}/bin/llama-box ] && file ${{ github.workspace }}/bin/llama-box && otool -L ${{ github.workspace }}/bin/llama-box | |
| echo "===== PACKAGE =====" | |
| cp LICENSE ${{ github.workspace }}/bin | |
| mkdir -p ${{ github.workspace }}/out | |
| zip -j ${{ github.workspace }}/out/llama-box-darwin-${{ matrix.arch }}-metal.zip ${{ github.workspace }}/bin/* | |
| - name: Upload Artifact | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| path: ${{ github.workspace }}/out/*.zip | |
| name: llama-box-darwin-${{ matrix.arch }}-metal | |
| linux-hip: | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| arch: [ amd64 ] | |
| version: [ '6.0.2' ] | |
| runs-on: ubuntu-22.04 | |
| steps: | |
| - name: Maximize Space | |
| # see https://github.com/easimon/maximize-build-space/blob/master/action.yml. | |
| run: | | |
| sudo rm -rf /usr/share/dotnet | |
| sudo rm -rf /usr/local/lib/android | |
| sudo rm -rf /opt/ghc | |
| sudo rm -rf /opt/hostedtoolcache/CodeQL | |
| sudo docker image prune --all --force | |
| - name: Clone | |
| uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 | |
| submodules: 'recursive' | |
| - name: Setup Cache | |
| timeout-minutes: 5 | |
| uses: actions/cache@v3 | |
| with: | |
| key: cache-linux-hip-${{ matrix.arch }}-${{ matrix.version }}-${{ hashFiles('**/.gitmodules') }} | |
| path: | | |
| ${{ github.workspace }}/.cache | |
| - name: Setup QEMU | |
| if: ${{ matrix.arch == 'arm64' }} | |
| uses: docker/setup-qemu-action@v3 | |
| with: | |
| image: tonistiigi/binfmt:qemu-v7.0.0 | |
| platforms: "arm64" | |
| - name: Build | |
| # disable OpenMP to support static linking, | |
| # see https://github.com/ggerganov/llama.cpp/issues/7743#issuecomment-2148342691, | |
| # https://github.com/ggerganov/llama.cpp/issues/7719#issuecomment-2147631216. | |
| # build fat binary, | |
| # see https://github.com/ggerganov/llama.cpp/pull/1087#issuecomment-1682807878, | |
| # https://llvm.org/docs/AMDGPUUsage.html. | |
| env: | |
| GPU_TARGETS: "gfx803;gfx900;gfx906;gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1010;gfx1030;gfx1100;gfx1101;gfx1102" | |
| run: | | |
| echo "===== SCRIPT =====" | |
| cat <<EOF > /tmp/entrypoint.sh | |
| #!/bin/bash | |
| apt-get update && apt-get install -y build-essential git rocblas-dev hipblas-dev libgomp1 ccache | |
| git config --global --add safe.directory /workspace/llama.cpp | |
| make -j LLAMA_HIPBLAS=1 LLAMA_NO_OPENMP=1 | |
| EOF | |
| chmod +x /tmp/entrypoint.sh | |
| cat /tmp/entrypoint.sh | |
| echo "===== BUILD =====" | |
| mkdir -p ${{ github.workspace }}/.cache | |
| docker run \ | |
| --rm \ | |
| --privileged \ | |
| --platform linux/${{ matrix.arch }} \ | |
| --volume ${{ github.workspace }}:/workspace \ | |
| --volume /tmp/entrypoint.sh:/entrypoint.sh \ | |
| --entrypoint /entrypoint.sh \ | |
| --workdir /workspace \ | |
| --env CCACHE_DIR=/workspace/.cache/ccache \ | |
| --env CC=/opt/rocm/llvm/bin/clang \ | |
| --env CXX=/opt/rocm/llvm/bin/clang++ \ | |
| --env GPU_TARGETS="${{ env.GPU_TARGETS }}" \ | |
| --env AMDGPU_TARGETS="${{ env.GPU_TARGETS }}" \ | |
| rocm/dev-ubuntu-22.04:${{ matrix.version }} | |
| echo "===== RESULT =====" | |
| [ -f ${{ github.workspace }}/bin/llama-box ] && file ${{ github.workspace }}/bin/llama-box && ldd ${{ github.workspace }}/bin/llama-box | |
| echo "===== PACKAGE =====" | |
| cp LICENSE ${{ github.workspace }}/bin | |
| mkdir -p ${{ github.workspace }}/out | |
| zip -j ${{ github.workspace }}/out/llama-box-linux-${{ matrix.arch }}-hip-${{ matrix.version }}.zip ${{ github.workspace }}/bin/* | |
| - name: Upload Artifact | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| path: ${{ github.workspace }}/out/*.zip | |
| name: llama-box-linux-${{ matrix.arch }}-hip-${{ matrix.version }} | |
| linux-cuda: | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| arch: [ amd64 ] | |
| version: [ '12.2.0', '11.7.1' ] | |
| runs-on: ubuntu-22.04 | |
| steps: | |
| - name: Maximize Space | |
| # see https://github.com/easimon/maximize-build-space/blob/master/action.yml. | |
| run: | | |
| sudo rm -rf /usr/share/dotnet | |
| sudo rm -rf /usr/local/lib/android | |
| sudo rm -rf /opt/ghc | |
| sudo rm -rf /opt/hostedtoolcache/CodeQL | |
| sudo docker image prune --all --force | |
| - name: Clone | |
| uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 | |
| submodules: 'recursive' | |
| - name: Setup Cache | |
| timeout-minutes: 5 | |
| uses: actions/cache@v3 | |
| with: | |
| key: cache-linux-cuda-${{ matrix.arch }}-${{ matrix.version }}-${{ hashFiles('**/.gitmodules') }} | |
| path: | | |
| ${{ github.workspace }}/.cache | |
| - name: Setup QEMU | |
| if: ${{ matrix.arch == 'arm64' }} | |
| uses: docker/setup-qemu-action@v3 | |
| with: | |
| image: tonistiigi/binfmt:qemu-v7.0.0 | |
| platforms: "arm64" | |
| - name: Build | |
| # disable OpenMP to support static linking, | |
| # see https://github.com/ggerganov/llama.cpp/issues/7743#issuecomment-2148342691, | |
| # https://github.com/ggerganov/llama.cpp/issues/7719#issuecomment-2147631216. | |
| run: | | |
| echo "===== SCRIPT =====" | |
| cat <<EOF > /tmp/entrypoint.sh | |
| #!/bin/bash | |
| apt-get update && apt-get install -y build-essential git libgomp1 ccache | |
| git config --global --add safe.directory /workspace/llama.cpp | |
| make -j LLAMA_CUDA=1 LLAMA_NO_OPENMP=1 | |
| EOF | |
| chmod +x /tmp/entrypoint.sh | |
| cat /tmp/entrypoint.sh | |
| echo "===== BUILD =====" | |
| mkdir -p ./.cache | |
| docker run \ | |
| --rm \ | |
| --privileged \ | |
| --platform linux/${{ matrix.arch }} \ | |
| --volume ${{ github.workspace }}:/workspace \ | |
| --workdir /workspace \ | |
| --volume /tmp/entrypoint.sh:/entrypoint.sh \ | |
| --entrypoint /entrypoint.sh \ | |
| --env CCACHE_DIR=/workspace/.cache/ccache \ | |
| --env CUDA_DOCKER_ARCH=all \ | |
| nvidia/cuda:${{ matrix.version }}-devel-ubuntu22.04 | |
| echo "===== RESULT =====" | |
| [ -f ${{ github.workspace }}/bin/llama-box ] && file ${{ github.workspace }}/bin/llama-box && ldd ${{ github.workspace }}/bin/llama-box | |
| echo "===== PACKAGE =====" | |
| cp LICENSE ${{ github.workspace }}/bin | |
| mkdir -p ${{ github.workspace }}/out | |
| zip -j ${{ github.workspace }}/out/llama-box-linux-${{ matrix.arch }}-cuda-${{ matrix.version }}.zip ${{ github.workspace }}/bin/* | |
| - name: Upload Artifact | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| path: ${{ github.workspace }}/out/*.zip | |
| name: llama-box-linux-${{ matrix.arch }}-cuda-${{ matrix.version }} | |
| release: | |
| if: ${{ startsWith(github.ref, 'refs/tags/') }} | |
| runs-on: ubuntu-22.04 | |
| needs: | |
| - darwin-metal | |
| - linux-hip | |
| - linux-cuda | |
| steps: | |
| - name: Download Artifact | |
| uses: actions/download-artifact@v4 | |
| with: | |
| path: ${{ github.workspace }}/out | |
| merge-multiple: true | |
| - name: Release | |
| uses: softprops/action-gh-release@v1 | |
| with: | |
| fail_on_unmatched_files: true | |
| tag_name: "${{ env.VERSION }}" | |
| prerelease: ${{ contains(github.ref, 'rc') }} | |
| files: ${{ github.workspace }}/out/* |