Build Release (CUDA) #86
Workflow file for this run
This file contains hidden or 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: Build Release (CUDA) | |
| on: workflow_dispatch | |
| permissions: | |
| contents: write | |
| jobs: | |
| build_wheels: | |
| name: Build Wheel CUDA ${{ matrix.cuda_config.ver }} Py ${{ matrix.pyver }} | |
| runs-on: ubuntu-latest | |
| container: | |
| image: nvidia/cuda:${{ matrix.cuda_config.ver }}-devel-ubuntu24.04 | |
| permissions: | |
| id-token: write | |
| contents: write | |
| attestations: write | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| cuda_config: | |
| - ver: 13.2.0 | |
| short: cu132 | |
| arch: 75 | |
| pyver: ["3.14"] | |
| defaults: | |
| run: | |
| shell: bash | |
| steps: | |
| - name: Install system dependencies | |
| run: | | |
| apt-get update | |
| apt-get install -y software-properties-common git curl build-essential cmake libssl-dev | |
| - name: Checkout repository | |
| uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5 | |
| with: | |
| submodules: recursive | |
| - name: Install UV and Python | |
| run: | | |
| curl -LsSf https://astral.sh/uv/install.sh | sh | |
| echo "$HOME/.local/bin" >> $GITHUB_PATH | |
| - name: Install Python | |
| run: | | |
| uv venv --python ${{ matrix.pyver }} | |
| echo "$GITHUB_WORKSPACE/.venv/bin" >> $GITHUB_PATH | |
| - name: Environment Diagnostics | |
| run: | | |
| echo "========== SYSTEM DIAGNOSTICS ==========" | |
| echo "GLIBC: $(ldd --version | head -n1)" | |
| echo "Python: $(python --version)" | |
| echo "uv: $(uv --version)" | |
| echo "CMake: $(cmake --version | head -n1)" | |
| echo "nvcc: $(nvcc --version 2>/dev/null | grep release || echo 'not found')" | |
| echo "Driver: $(nvidia-smi --query-gpu=driver_version --format=csv,noheader 2>/dev/null || echo 'not available')" | |
| echo "========================================" | |
| - name: Build Wheel | |
| working-directory: vendor/llama-cpp-python | |
| env: | |
| VERBOSE: 1 | |
| CMAKE_ARGS: >- | |
| -DGGML_CUDA=on | |
| -DLLAVA_BUILD=off | |
| -DCMAKE_CUDA_ARCHITECTURES=${{ matrix.cuda_config.arch }} | |
| -DGGML_CUDA_FORCE_MMQ=OFF | |
| -DGGML_AVX2=on | |
| -DGGML_FMA=on | |
| -DGGML_F16C=on | |
| -DLLAMA_BUILD_EXAMPLES=OFF | |
| -DLLAMA_BUILD_TESTS=OFF | |
| -DLLAMA_BUILD_SERVER=OFF | |
| -DCMAKE_EXE_LINKER_FLAGS="-L/usr/local/cuda/lib64/stubs -lcuda" | |
| run: | | |
| # Rename the release version with +cu{cuda_ver} build tag | |
| sed -i 's/__version__ = "\([^"]*\)"/__version__ = "\1+${{ matrix.cuda_config.short }}"/' llama_cpp/__init__.py | |
| # Build wheel using uv | |
| uv -v build --no-create-gitignore --python cpython@${{ matrix.pyver }} --wheel | |
| - name: List built wheels | |
| run: ls -lh vendor/llama-cpp-python/dist/*.whl | |
| - name: Upload Release Assets | |
| uses: softprops/action-gh-release@5be0e66d93ac7ed76da52eca8bb058f665c3a5fe # v2 | |
| with: | |
| files: vendor/llama-cpp-python/dist/*.whl | |
| tag_name: ${{ github.ref_name }} | |
| env: | |
| GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| - name: Attest Build Provenance | |
| uses: actions/attest-build-provenance@977bb373ede98d70efdf65b84cb5f73e068dcc2a # v3 | |
| with: | |
| subject-path: 'vendor/llama-cpp-python/dist/*.whl' |