name: Setup Python & Install
description: Sets up Python and installs project dependencies.
inputs:
  python-version:
    description: 'Python version to use'
    required: false
    default: '3.12'
  key:
    description: 'Key for the python cache'
    required: false
    default: ''  # if you don't set a key, it doesn't cache
  deps:
    description: 'Extra dependency groups (comma separated)'
    required: false
    default: ''
  pydeps:
    description: 'Extra Python dependency groups (space separated)'
    required: false
    default: ''
  opencl:
    description: "Install OpenCL?"
    required: false
    default: 'false'
  amd:
    description: "Install AMD?"
    required: false
    default: 'false'
  cuda:
    description: "Install CUDA?"
    required: false
    default: 'false'
  ocelot:
    description: "Install gpuocelot?"
    required: false
    default: 'false'
  webgpu:
    description: "Install webgpu?"
    required: false
    default: 'false'
  llvm:
    description: "Install LLVM?"
    required: false
    default: 'false'
runs:
  using: "composite"
  steps:
    - name: Set up Python ${{ inputs.python-version }}
      id: setup-python
      uses: actions/setup-python@v5
      with:
        python-version: ${{ inputs.python-version }}

    # **** Caching packages ****

    - name: Cache Python packages
      id: restore-venv
      uses: actions/cache@v4
      with:
        path: ${{ github.workspace }}/.venv
        key: venv-${{ runner.os }}-python-${{ steps.setup-python.outputs.python-version }}-${{ inputs.deps }}-${{ inputs.pydeps }}-${{ hashFiles('**/setup.py') }}-${{ env.PYTHON_CACHE_VERSION }}

    # **** Caching downloads ****

    - name: Cache downloads (Linux)
      if: inputs.key != '' && runner.os == 'Linux'
      uses: actions/cache@v4
      with:
        path: ~/.cache/tinygrad/downloads/
        key: downloads-cache-${{ inputs.key }}-${{ env.DOWNLOAD_CACHE_VERSION }}
    - name: Cache downloads (macOS)
      if: inputs.key != '' && runner.os == 'macOS'
      uses: actions/cache@v4
      with:
        path: ~/Library/Caches/tinygrad/downloads/
        key: osx-downloads-cache-${{ inputs.key }}-${{ env.DOWNLOAD_CACHE_VERSION }}

    # **** Python deps ****

    - name: Install dependencies in venv (with extra)
      if: inputs.deps != '' && steps.restore-venv.outputs.cache-hit != 'true'
      shell: bash
      run: |
        python -m venv .venv
        if [[ "$RUNNER_OS" == "Windows" ]]; then
          source .venv/Scripts/activate
        else
          . .venv/bin/activate
        fi
        python -m pip install -e ".[${{ inputs.deps }}]" ${{ inputs.pydeps }} --extra-index-url https://download.pytorch.org/whl/cpu --extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/Triton-Nightly/pypi/simple/
    - name: Install dependencies in venv (without extra)
      if: inputs.deps == '' && steps.restore-venv.outputs.cache-hit != 'true'
      shell: bash
      run: |
        python -m venv .venv
        if [[ "$RUNNER_OS" == "Windows" ]]; then
          source .venv/Scripts/activate
        else
          . .venv/bin/activate
        fi
        python -m pip install -e . ${{ inputs.pydeps }}
    - name: Set up venv environment
      shell: bash
      run: |
        echo "VIRTUAL_ENV=${{ github.workspace }}/.venv" >> "$GITHUB_ENV"
        echo "OMP_NUM_THREADS=1" >> "$GITHUB_ENV"
        # no buffers should be over 300MB in CI
        echo "MAX_BUFFER_SIZE=300000000" >> "$GITHUB_ENV"
        if [[ "$RUNNER_OS" == "Windows" ]]; then
          echo "${{ github.workspace }}/.venv/Scripts" >> "$GITHUB_PATH"
        else
          echo "${{ github.workspace }}/.venv/bin" >> "$GITHUB_PATH"
        fi

    # ******************* apt *******************

    - name: Add OpenCL Repo
      if: inputs.opencl == 'true' && runner.os == 'Linux'
      shell: bash
      run: echo "deb [ allow-insecure=yes ] https://apt.repos.intel.com/oneapi all main" | sudo tee /etc/apt/sources.list.d/oneAPI.list

    - name: Add AMD Repo (Linux)
      if: inputs.amd == 'true' && runner.os == 'Linux'
      shell: bash
      run: |
        wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
        sudo tee /etc/apt/sources.list.d/rocm.list <<EOF
        deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/6.2 $(lsb_release -cs) main
        EOF
        echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600

    - name: Add LLVM Repo (Linux)
      if: inputs.llvm == 'true' && runner.os == 'Linux'
      shell: bash
      run: |
        wget -qO- https://apt.llvm.org/llvm-snapshot.gpg.key | sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc
        echo "deb http://apt.llvm.org/$(lsb_release -cs)/ llvm-toolchain-$(lsb_release -cs)-20 main" | sudo tee /etc/apt/sources.list.d/llvm.list

    - name: apt-get update + install
      if: runner.os == 'Linux' && (inputs.opencl == 'true' || inputs.amd == 'true' || inputs.cuda == 'true' || inputs.webgpu == 'true' || inputs.llvm == 'true')
      shell: bash
      run: |
        echo 'Acquire::GzipIndexes "true";' | sudo tee /etc/apt/apt.conf.d/gzip
        echo 'Acquire::http::Pipeline-Depth "5";' | sudo tee -a /etc/apt/apt.conf.d/99parallel
        sudo apt -qq update || true

        pkgs=""
        # **** OpenCL ****
        if [[ "${{ inputs.opencl }}" == "true" ]]; then
          pkgs+=" opencl-headers \
            intel-oneapi-runtime-openmp=2023.2.1-16 intel-oneapi-runtime-compilers-common=2023.2.1-16 intel-oneapi-runtime-compilers=2023.2.1-16 \
            intel-oneapi-runtime-dpcpp-sycl-opencl-cpu=2023.2.1-16 intel-oneapi-runtime-tbb-common=2021.10.0-49541 \
            intel-oneapi-runtime-tbb=2021.10.0-49541 intel-oneapi-runtime-opencl=2023.2.1-16"
        fi
        # **** AMD ****
        if [[ "${{ inputs.amd }}" == "true" ]]; then
          pkgs+=" hsa-rocr comgr hsa-rocr-dev liburing-dev libibverbs-dev libc6-dev"
        fi
        # **** CUDA ****
        if [[ "${{ inputs.cuda }}" == "true" ]]; then
          pkgs+=" git g++ cmake ninja-build llvm-15-dev zlib1g-dev libglew-dev \
            flex bison libfl-dev libboost-thread-dev libboost-filesystem-dev nvidia-cuda-toolkit-gcc libzstd-dev"
        fi
        # **** WebGPU (dependencies for software-based vulkan) ****
        if [[ "${{ inputs.webgpu }}" == "true" ]]; then
          pkgs+=" libgl1 libglx-mesa0 libgl1-mesa-dri libxcb-xfixes0-dev mesa-vulkan-drivers"
        fi
        # **** LLVM ****
        if [[ "${{ inputs.llvm }}" == "true" ]]; then
          pkgs+=" libllvm20 clang-20 lld-20"
        fi

        # ******** do install ********
        if [[ -n "$pkgs" ]]; then
          sudo apt-get -y --allow-unauthenticated --no-install-recommends install $pkgs
        fi

    # **** AMD ****

    - name: Setup AMD (Linux)
      if: inputs.amd == 'true' && runner.os == 'Linux'
      shell: bash
      run: |
        cargo build --release --manifest-path ./extra/remu/Cargo.toml
        sudo ln -sf ${{ github.workspace }}/extra/remu/target/release/libremu.so /usr/local/lib/libremu.so
        sudo tee --append /etc/ld.so.conf.d/rocm.conf <<'EOF'
          /opt/rocm/lib
          /opt/rocm/lib64
        EOF
        sudo ldconfig
    - name: Setup AMD comgr+remu (macOS)
      if: inputs.amd == 'true' && runner.os == 'macOS'
      shell: bash
      run: |
        sudo mkdir -p /usr/local/lib
        curl -s -H "Authorization: token $GH_TOKEN" curl -s https://api.github.com/repos/nimlgen/amdcomgr_dylib/releases/latest | \
          jq -r '.assets[] | select(.name == "libamd_comgr.dylib").browser_download_url' | \
          sudo xargs curl -L -o /usr/local/lib/libamd_comgr.dylib
        cargo build --release --manifest-path ./extra/remu/Cargo.toml

    # **** gpuocelot ****

    - name: Install gpuocelot dependencies (MacOS)
      if: inputs.ocelot == 'true' && runner.os == 'macOS'
      shell: bash
      run: brew install --quiet cmake ninja llvm@15 zlib glew flex bison boost zstd ncurses
    - name: Cache gpuocelot
      if: inputs.ocelot == 'true'
      id: cache-build
      uses: actions/cache@v4
      env:
        cache-name: cache-gpuocelot-build
      with:
        path: ${{ github.workspace }}/gpuocelot/ocelot
        key: ${{ runner.os }}-gpuocelot-b16039dc940dc6bc4ea0a98380495769ff35ed99-rebuild-0
    - name: Clone/compile gpuocelot
      if: inputs.ocelot == 'true' && steps.cache-build.outputs.cache-hit != 'true'
      shell: bash
      run: |
        git clone --recurse-submodules https://github.com/gpuocelot/gpuocelot.git ${{ github.workspace }}/gpuocelot
        cd ${{ github.workspace }}/gpuocelot/ocelot
        git checkout b16039dc940dc6bc4ea0a98380495769ff35ed99
        mkdir build
        cd build
        cmake .. -Wno-dev -G Ninja -DOCELOT_BUILD_TOOLS=OFF -DCMAKE_BUILD_ALWAYS=0 -DBUILD_TESTS_CUDA=OFF -DCMAKE_POLICY_VERSION_MINIMUM=3.5
        ninja
    - name: Install gpuocelot
      if: inputs.ocelot == 'true'
      shell: bash
      run: |
        cd ${{ github.workspace }}/gpuocelot/ocelot/build
        sudo cp libgpuocelot.${{ runner.os == 'macOS' && 'dylib' || 'so' }} /usr/${{ runner.os == 'macOS' && 'local/' || ''}}lib/

    # **** WebGPU ****

    - name: Install WebGPU dawn (Linux)
      if: inputs.webgpu == 'true' && runner.os == 'Linux'
      shell: bash
      run: |
        sudo curl -L https://github.com/wpmed92/pydawn/releases/download/v0.1.6/libwebgpu_dawn.so -o /usr/local/lib/libwebgpu_dawn.so
        sudo ldconfig
    - name: Install WebGPU dawn (macOS)
      if: inputs.webgpu == 'true' && runner.os == 'macOS'
      shell: bash
      run: |
        brew tap wpmed92/dawn
        brew install dawn

    # **** LLVM ****

    - name: Install LLVM (macOS)
      if: inputs.llvm == 'true' && runner.os == 'macOS'
      shell: bash
      run: brew install llvm@20