llama.cpp/.github/workflows/ci-self-hosted-webgpu.yml

name: CI (self-hosted WebGPU backend)

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

  pull_request:
    types: [opened, synchronize, reopened]
    paths: [
      '.github/workflows/ci-self-hosted-webgpu.yml',
      'ci/run.sh',
      '**/CMakeLists.txt',
      '**/.cmake',
      'ggml/src/*',
      'ggml/src/ggml-cpu/**',
      'ggml/src/ggml-webgpu/**'
    ]

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

env:
  # note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)
  HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
  GGML_NLOOP: 3
  GGML_N_THREADS: 1
  LLAMA_ARG_LOG_COLORS: 1
  LLAMA_ARG_LOG_PREFIX: 1
  LLAMA_ARG_LOG_TIMESTAMPS: 1

jobs:
  gpu-webgpu-nvidia:
    runs-on: "hf-jobs-t4-small:ubuntu26_04"

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

      - name: Install dependencies
        run: |
          sudo apt update
          sudo apt install -y build-essential cmake libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libvulkan1 mesa-vulkan-drivers libglvnd0 libgl1 libglx0 libegl1 libgles2 libssl-dev time unzip wget python3 python3-venv python3-pip

      - name: ccache
        uses: ggml-org/ccache-action@v1.2.24
        with:
          restore: false
          save: false

      - name: ccache-buckets-restore
        uses: ./.github/actions/ccache-buckets
        with:
          key: self-hosted-webgpu-nvidia
          folder: llama.cpp
          hf_bucket: ggml-org/cache

      - name: Dawn Dependency
        id: dawn-depends
        run: |
          DAWN_VERSION="v20260908.214631"
          DAWN_OWNER="google"
          DAWN_REPO="dawn"
          DAWN_ASSET_NAME="Dawn-94c3c9cc0d5fb2e85aebb370fa8d37b71aa34655-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: Test
        id: ggml-ci
        run: |
          GG_BUILD_WEBGPU=1 \
          GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \
          GG_BUILD_WEBGPU_DAWN_DIR="$GITHUB_WORKSPACE/dawn/lib64/cmake/Dawn" \
            bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

      - name: ccache-buckets-save
        if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
        uses: ./.github/actions/ccache-buckets
        env:
          HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
        with:
          key: self-hosted-webgpu-nvidia
          folder: llama.cpp
          evict-old-files: 1d
          hf_bucket: ggml-org/cache
          save: true

  gpu-webgpu-apple:
    runs-on: [self-hosted, macOS, ARM64]

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

      - name: Dawn Dependency
        id: dawn-depends
        run: |
          DAWN_VERSION="v20260908.214631"
          DAWN_OWNER="google"
          DAWN_REPO="dawn"
          DAWN_ASSET_NAME="Dawn-94c3c9cc0d5fb2e85aebb370fa8d37b71aa34655-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: Test
        id: ggml-ci
        run: |
          GG_BUILD_WEBGPU=1 GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \
            bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp