char-fork/llama.cpp

git clone https://git.t4t.associates/char-fork/llama.cpp

Mendy Bergerggml-webgpu: Update to a recent version of Dawn (#28683)d3146f2b52026-09-11

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',
      '**/*.tmpl',
      'ggml/src/ggml-webgpu/wgsl-shaders/embed_wgsl.py'
    ]

  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_ARG_LOG_COLORS: 1
  LLAMA_ARG_LOG_PREFIX: 1
  LLAMA_ARG_LOG_TIMESTAMPS: 1

jobs:
  format:
    runs-on: ubuntu-24.04

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

      - name: Install clang-format 22
        run: |
          wget -qO- https://apt.llvm.org/llvm-snapshot.gpg.key |
            sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc > /dev/null
          sudo add-apt-repository -y \
            "deb http://apt.llvm.org/noble/ llvm-toolchain-noble-22 main"
          sudo apt-get update
          sudo apt-get install -y clang-format-22

      - name: Check formatting
        run: |
          find ggml/src/ggml-webgpu \
            -type f \( -name '*.cpp' -o -name '*.hpp' -o -name '*.h' \) \
            -print0 |
            xargs -0 clang-format-22 --dry-run --Werror

  macos:
    runs-on: macos-latest

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

      - name: ccache
        uses: ggml-org/ccache-action@v1.2.24
        with:
          key: webgpu-macos-latest
          save: false

      - 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: ccache-buckets-restore
        uses: ./.github/actions/ccache-buckets
        env:
          HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
        with:
          key: webgpu-macos-latest
          folder: llama.cpp
          hf_bucket: ggml-org/cache

      - 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: 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: webgpu-macos-latest
          folder: llama.cpp
          evict-old-files: 1d
          hf_bucket: ggml-org/cache
          save: true

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

  ubuntu:
    runs-on: ubuntu-24.04

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

      - name: ccache
        uses: ggml-org/ccache-action@v1.2.24
        with:
          key: webgpu-ubuntu-24.04
          save: false

      - 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: 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="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: ccache-buckets-restore
        uses: ./.github/actions/ccache-buckets
        env:
          HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
        with:
          key: webgpu-ubuntu-24.04
          folder: llama.cpp
          hf_bucket: ggml-org/cache

      - 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: 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: webgpu-ubuntu-24.04
          folder: llama.cpp
          evict-old-files: 1d
          hf_bucket: ggml-org/cache
          save: true

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