llama-cpp-python/.github/workflows/build-and-release.yaml

name: Build Release

on: workflow_dispatch

permissions:
  contents: write

jobs:
  build_wheels:
    name: Build wheels on ${{ matrix.os }}
    runs-on: ${{ matrix.os }}
    strategy:
      matrix:
        os: [ubuntu-22.04, windows-2022, macos-14, macos-15]

    steps:
      - uses: actions/checkout@v4
        with:
          submodules: "recursive"

      # Used to host cibuildwheel
      - uses: actions/setup-python@v5
        with:
          python-version: "3.9"

      - name: Install dependencies (Linux/MacOS)
        if: runner.os != 'Windows'
        run: |
          python -m pip install --upgrade pip
          python -m pip install uv
          RUST_LOG=trace python -m uv pip install -e .[all] --verbose
        shell: bash

      - name: Install dependencies (Windows)
        if: runner.os == 'Windows'
        env:
          RUST_LOG: trace        
        run: |
          python -m pip install --upgrade pip
          python -m pip install uv
          python -m uv pip install -e .[all] --verbose
        shell: cmd

      - name: Build wheels
        uses: pypa/cibuildwheel@v2.22.0
        env:
          # disable repair
          CIBW_REPAIR_WHEEL_COMMAND: ""
          # Skip cibuildwheel's default i686 sidecar and keep Linux release
          # wheels on a portable x86_64 CPU baseline.
          CIBW_ARCHS_LINUX: "auto64"
          CIBW_ENVIRONMENT_LINUX: CMAKE_ARGS="-DGGML_NATIVE=off"
          # Keep macOS release wheels on a portable CPU baseline instead of
          # inheriting the hosted runner's native flags.
          CIBW_ENVIRONMENT_MACOS: CMAKE_ARGS="-DGGML_NATIVE=off"
        with:
          package-dir: .
          output-dir: wheelhouse

      - uses: actions/upload-artifact@v4
        with:
          name: wheels-${{ matrix.os }}
          path: ./wheelhouse/*.whl

  build_wheels_arm64:
    name: Build arm64 wheels
    runs-on: ubuntu-24.04-arm
    steps:
      - uses: actions/checkout@v4
        with:
          submodules: "recursive"

      - name: Build wheels
        uses: pypa/cibuildwheel@v2.22.0
        env:
          CIBW_SKIP: "*musllinux* pp*"
          CIBW_REPAIR_WHEEL_COMMAND: ""
          CIBW_ARCHS: "aarch64"
          # Keep native arm64 builds on a portable CPU baseline instead of
          # tuning wheels to the hosted runner.
          CIBW_ENVIRONMENT: CMAKE_ARGS="-DGGML_NATIVE=off"
          CIBW_BUILD: "cp38-* cp39-* cp310-* cp311-* cp312-*"
        with:
          output-dir: wheelhouse

      - name: Upload wheels as artifacts
        uses: actions/upload-artifact@v4
        with:
          name: wheels_arm64
          path: ./wheelhouse/*.whl

  build_wheels_riscv64:
    name: Build riscv64 wheels (${{ matrix.shard.name }})
    runs-on: ubuntu-latest
    strategy:
      fail-fast: false
      matrix:
        shard:
          - name: cp310
            build: "cp310-*"
            artifact: wheels_riscv64_cp310
          - name: cp311
            build: "cp311-*"
            artifact: wheels_riscv64_cp311
          - name: cp312
            build: "cp312-*"
            artifact: wheels_riscv64_cp312
          - name: cp313
            build: "cp313-*"
            artifact: wheels_riscv64_cp313
          - name: cp314
            build: "cp314-*"
            artifact: wheels_riscv64_cp314
    steps:
      - uses: actions/checkout@v4
        with:
          submodules: "recursive"

      - name: Set up QEMU
        uses: docker/setup-qemu-action@v3
        with:
          platforms: linux/riscv64

      - name: Build wheels
        uses: pypa/cibuildwheel@v3.1.2
        env:
          CIBW_SKIP: "*musllinux* pp*"
          CIBW_REPAIR_WHEEL_COMMAND: ""
          CIBW_ARCHS: "riscv64"
          # Build riscv64 wheels against a conservative baseline instead of
          # enabling RVV-related extensions from the build container.
          CIBW_ENVIRONMENT: CMAKE_ARGS="-DGGML_NATIVE=off -DGGML_RVV=off -DGGML_RV_ZFH=off -DGGML_RV_ZVFH=off -DGGML_RV_ZICBOP=off -DGGML_RV_ZIHINTPAUSE=off"
          # Split the emulated riscv64 build into one Python version per job
          # to minimize wall-clock time without changing the release artifacts.
          CIBW_BUILD: ${{ matrix.shard.build }}
        with:
          output-dir: wheelhouse

      - name: Upload wheels as artifacts
        uses: actions/upload-artifact@v4
        with:
          name: ${{ matrix.shard.artifact }}
          path: ./wheelhouse/*.whl

  build_sdist:
    name: Build source distribution
    runs-on: ubuntu-latest

    steps:
      - uses: actions/checkout@v4
        with:
          submodules: "recursive"

      - uses: actions/setup-python@v5
        with:
          python-version: "3.9"

      - name: Install dependencies (Linux/MacOS)
        if: runner.os != 'Windows'
        run: |
          python -m pip install --upgrade pip
          python -m pip install uv
          RUST_LOG=trace python -m uv pip install -e .[all] --verbose
          python -m uv pip install build
        shell: bash

      - name: Install dependencies (Windows)
        if: runner.os == 'Windows'
        env:
          RUST_LOG: trace        
        run: |
          python -m pip install --upgrade pip
          python -m pip install uv
          python -m uv pip install -e .[all] --verbose
          python -m uv pip install build
        shell: cmd

      - name: Build source distribution
        run: |
          python -m build --sdist

      - uses: actions/upload-artifact@v4
        with:
          name: sdist
          path: ./dist/*.tar.gz

  release:
    name: Release
    needs: [build_wheels, build_wheels_arm64, build_wheels_riscv64, build_sdist]
    if: startsWith(github.ref, 'refs/tags/')
    runs-on: ubuntu-latest

    steps:
      - uses: actions/download-artifact@v4
        with:
          merge-multiple: true
          path: dist

      - uses: softprops/action-gh-release@v2
        with:
          files: dist/*
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}