name: CI (CUDA, windows)

# TODO: this workflow is only triggered manually because it is very heavy on the CI
#       when we provision dedicated windows runners, we can enable it for pushes too
# note: running this workflow manually will populate the ccache for the release builds
#       this can be used before merging a PR to speed up the release workflow
on:
  workflow_dispatch: # allows manual triggering

# note: this will run in queue with the release workflow
concurrency:
  group: release
  queue: max

env:
  GH_TOKEN: ${{ github.token }}
  GGML_NLOOP: 3
  GGML_N_THREADS: 1
  LLAMA_ARG_LOG_COLORS: 1
  LLAMA_ARG_LOG_PREFIX: 1
  LLAMA_ARG_LOG_TIMESTAMPS: 1

jobs:
  cuda:
    runs-on: windows-2022

    permissions:
      actions: write

    strategy:
      matrix:
        cuda: ['12.4', '13.3']

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v6

      - name: ccache
        uses: ggml-org/ccache-action@v1.2.21
        with:
          key: release-windows-2022-x64-cuda-${{ matrix.cuda }}

      - name: Install Cuda Toolkit
        uses: ./.github/actions/windows-setup-cuda
        with:
          cuda_version: ${{ matrix.cuda }}

      - name: Install Ninja
        id: install_ninja
        run: |
          choco install ninja

      - name: Build
        id: cmake_build
        shell: cmd
        # TODO: Remove GGML_CUDA_CUB_3DOT2 flag once CCCL 3.2 is bundled within CTK and that CTK version is used in this project
        run: |
          call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvarsall.bat" x64
          cmake -S . -B build -G "Ninja Multi-Config" ^
            -DLLAMA_BUILD_SERVER=ON ^
            -DLLAMA_BUILD_BORINGSSL=ON ^
            -DGGML_NATIVE=OFF ^
            -DGGML_BACKEND_DL=ON ^
            -DGGML_CPU_ALL_VARIANTS=ON ^
            -DGGML_CUDA=ON ^
            -DGGML_RPC=ON ^
            -DGGML_CUDA_CUB_3DOT2=ON
          set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
          cmake --build build --config Release -j %NINJA_JOBS% -t ggml
          cmake --build build --config Release

      - name: ccache-clear
        uses: ./.github/actions/ccache-clear
        with:
          key: release-windows-2022-x64-cuda-${{ matrix.cuda }}

  hip:
    runs-on: windows-2022

    permissions:
      actions: write

    env:
      # Make sure this is in sync with build-cache.yml
      HIPSDK_INSTALLER_VERSION: "26.Q1"

    strategy:
      matrix:
        include:
          # sync with release.yml
          - name: "radeon"
            gpu_targets: "gfx1150;gfx1151;gfx1200;gfx1201;gfx1100;gfx1101;gfx1102;gfx1030;gfx1031;gfx1032"

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v6

      - name: Grab rocWMMA package
        id: grab_rocwmma
        run: |
          curl -o rocwmma.deb "https://repo.radeon.com/rocm/apt/7.2.1/pool/main/r/rocwmma-dev/rocwmma-dev_2.2.0.70201-81~24.04_amd64.deb"
          7z x rocwmma.deb
          7z x data.tar

      - name: Use ROCm Installation Cache
        uses: actions/cache@v5
        id: cache-rocm
        with:
          path: C:\Program Files\AMD\ROCm
          key: cache-gha-rocm-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ runner.os }}

      - name: Setup ROCm
        if: steps.cache-rocm.outputs.cache-hit != 'true'
        uses: ./.github/actions/windows-setup-rocm
        with:
          version: ${{ env.HIPSDK_INSTALLER_VERSION }}

      - name: Verify ROCm
        id: verify
        run: |
          # Find and test ROCm installation
          $clangPath = Get-ChildItem 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | Select-Object -First 1
          if (-not $clangPath) {
            Write-Error "ROCm installation not found"
            exit 1
          }
          & $clangPath.FullName --version

      - name: ccache
        uses: ggml-org/ccache-action@v1.2.21
        with:
          # TODO: this build does not match the build in release.yml, so we use a different cache key
          #       ideally, the builds should match, similar to the CUDA build above so that we would be able
          #       to populate the ccache for the release with manual runs of this workflow
          #key: release-windows-2022-x64-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}
          key: cuda-windows-2022-x64-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}

      - name: Build
        id: cmake_build
        run: |
          $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path)
          $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}"
          cmake -G "Unix Makefiles" -B build -S . `
            -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" `
            -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" `
            -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/opt/rocm-7.2.1/include/" `
            -DCMAKE_BUILD_TYPE=Release `
            -DLLAMA_BUILD_BORINGSSL=ON `
            -DROCM_DIR="${env:HIP_PATH}" `
            -DGGML_HIP=ON `
            -DGGML_HIP_ROCWMMA_FATTN=ON `
            -DGPU_TARGETS="gfx1100"  `
            -DGGML_RPC=ON
          cmake --build build -j ${env:NUMBER_OF_PROCESSORS}

      - name: ccache-clear
        uses: ./.github/actions/ccache-clear
        with:
          #key: release-windows-2022-x64-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}
          key: cuda-windows-2022-x64-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}