koboldcpp/.github/workflows/build-webgpu.yml

name: CI (webgpu)

on:
  workflow_dispatch: # allows manual triggering
  push:
    branches:
      - master
    paths: [
      '.github/workflows/build-webgpu.yml',
      '**/CMakeLists.txt',
      '**/.cmake',
      '**/*.h',
      '**/*.hpp',
      '**/*.c',
      '**/*.cpp',
      '**/*.wgsl'
    ]

  pull_request:
    types: [opened, synchronize, reopened]
    paths: [
      '.github/workflows/build-webgpu.yml',
      'ggml/src/ggml-webgpu/**'
    ]

concurrency:
  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
  cancel-in-progress: true

env:
  GGML_NLOOP: 3
  GGML_N_THREADS: 1
  LLAMA_LOG_COLORS: 1
  LLAMA_LOG_PREFIX: 1
  LLAMA_LOG_TIMESTAMPS: 1

jobs:

  macOS-latest-arm64-webgpu:
    runs-on: macos-latest

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

      - name: ccache
        uses: ggml-org/ccache-action@v1.2.21
        with:
          key: macOS-latest-arm64-webgpu
          evict-old-files: 1d
          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}

      - name: Dawn Dependency
        id: dawn-depends
        run: |
          DAWN_VERSION="v20260317.182325"
          DAWN_OWNER="google"
          DAWN_REPO="dawn"
          DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-macos-latest-Release"
          echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
          curl -L -o artifact.tar.gz \
            "https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
          mkdir dawn
          tar -xvf artifact.tar.gz -C dawn --strip-components=1

      - name: Build
        id: cmake_build
        run: |
          export CMAKE_PREFIX_PATH=dawn
          cmake -B build -G "Ninja" -DCMAKE_BUILD_TYPE=Release -DGGML_WEBGPU=ON -DGGML_METAL=OFF -DGGML_BLAS=OFF
          time cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)

      - name: Test
        id: cmake_test
        run: |
          cd build
          ctest -L main --verbose --timeout 900

  ubuntu-24-webgpu:
    runs-on: ubuntu-24.04

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

      - name: ccache
        uses: ggml-org/ccache-action@v1.2.21
        with:
          key: ubuntu-24-webgpu
          evict-old-files: 1d
          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}

      - name: Dependencies
        id: depends
        run: |
          sudo add-apt-repository -y ppa:kisak/kisak-mesa
          sudo apt-get update -y
          sudo apt-get install -y build-essential mesa-vulkan-drivers \
            libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libssl-dev

      - name: Get latest Vulkan SDK version
        id: vulkan_sdk_version
        run: |
          echo "VULKAN_SDK_VERSION=$(curl https://vulkan.lunarg.com/sdk/latest/linux.txt)" >> "$GITHUB_ENV"

      - name: Use Vulkan SDK Cache
        uses: actions/cache@v5
        id: cache-sdk
        with:
          path: ./vulkan_sdk
          key: cache-gha-vulkan-sdk-${{ env.VULKAN_SDK_VERSION }}-${{ runner.os }}

      - name: Setup Vulkan SDK
        if: steps.cache-sdk.outputs.cache-hit != 'true'
        uses: ./.github/actions/linux-setup-vulkan
        with:
          path: ./vulkan_sdk
          version: ${{ env.VULKAN_SDK_VERSION }}

      - name: Dawn Dependency
        id: dawn-depends
        run: |
          sudo apt-get install -y libxrandr-dev libxinerama-dev libxcursor-dev mesa-common-dev libx11-xcb-dev libxi-dev
          DAWN_VERSION="v20260317.182325"
          DAWN_OWNER="google"
          DAWN_REPO="dawn"
          DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-ubuntu-latest-Release"
          echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
          curl -L -o artifact.tar.gz \
            "https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
          mkdir dawn
          tar -xvf artifact.tar.gz -C dawn --strip-components=1

      - name: Build
        id: cmake_build
        run: |
          export Dawn_DIR=dawn/lib64/cmake/Dawn
          cmake -B build \
            -DGGML_WEBGPU=ON
          time cmake --build build --config Release -j $(nproc)

      - name: Test
        id: cmake_test
        run: |
          cd build
          # This is using llvmpipe and runs slower than other backends
          # test-backend-ops is too slow on llvmpipe, skip it
          ctest -L main -E test-backend-ops --verbose --timeout 900

  ubuntu-24-webgpu-wasm:
    runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}

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

      - name: Install Emscripten
        run: |
          git clone https://github.com/emscripten-core/emsdk.git
          cd emsdk
          ./emsdk install latest
          ./emsdk activate latest

      - name: Fetch emdawnwebgpu
        run: |
          DAWN_TAG="v20260317.182325"
          EMDAWN_PKG="emdawnwebgpu_pkg-${DAWN_TAG}.zip"
          echo "Downloading ${EMDAWN_PKG}"
          curl -L -o emdawn.zip \
            "https://github.com/google/dawn/releases/download/${DAWN_TAG}/${EMDAWN_PKG}"
          unzip emdawn.zip

      - name: Build WASM WebGPU
        run: |
          source emsdk/emsdk_env.sh
          emcmake cmake -B build-wasm \
            -G "Ninja" \
            -DCMAKE_BUILD_TYPE=Release \
            -DGGML_WEBGPU=ON \
            -DLLAMA_OPENSSL=OFF \
            -DEMDAWNWEBGPU_DIR=emdawnwebgpu_pkg

          time cmake --build build-wasm --config Release --target test-backend-ops -j $(nproc)