name: CI (wasi)

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

cache-mode: none
permissions:
  contents: read

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

env:
  WASI_SDK_VERSION: 34
  DAWN_VERSION: v20260908.214631
  DAWN_COMMIT: 94c3c9cc0d5fb2e85aebb370fa8d37b71aa34655
  WASI_WEBGPU_HEADERS_COMMIT: 917765edd7cb8f8cf95bda1217514c78f71b582b

jobs:
  ubuntu-webgpu:
    runs-on: ubuntu-24.04-arm

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

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

      - name: Install wasi-sdk
        uses: bytecodealliance/setup-wasi-sdk-action@77d09f3df1e8da344d8403cf8631af8977938b4c # v1.0.0
        with:
          version: ${{ env.WASI_SDK_VERSION }}
          add-to-path: false

      - name: wasi:webgpu Dependency
        run: |
          mkdir -p wasi-webgpu/dawn-headers
          curl -fL "https://github.com/google/dawn/releases/download/${DAWN_VERSION}/dawn-headers-${DAWN_COMMIT}.tar.gz" |
            tar -xz -C wasi-webgpu/dawn-headers --strip-components=1

          git init -q wasi-webgpu/wasi-webgpu-headers
          cd wasi-webgpu/wasi-webgpu-headers
          git fetch -q --depth 1 https://github.com/wasi-gfx/wasi-webgpu-headers.git ${WASI_WEBGPU_HEADERS_COMMIT}
          git checkout -q FETCH_HEAD
          git submodule update -q --init --depth 1
          cd ../..

          # ggml-webgpu does find_package(Dawn) and links dawn::webgpu_dawn. There is no Dawn on WASI,
          # so this target instead compiles wasi-webgpu-headers (webgpu.h over wasi:webgpu imports)
          # and exposes Dawn's webgpu_cpp.h on top of it.
          cat > wasi-webgpu/DawnConfig.cmake << 'EOF'
          set(_wasi_webgpu "${CMAKE_CURRENT_LIST_DIR}/wasi-webgpu-headers")
          add_library(dawn::webgpu_dawn INTERFACE IMPORTED)
          set_target_properties(dawn::webgpu_dawn PROPERTIES
              INTERFACE_SOURCES "${_wasi_webgpu}/webgpu.c;${_wasi_webgpu}/async_futures.c;${_wasi_webgpu}/imports.c;${_wasi_webgpu}/imports_component_type.o"
              INTERFACE_INCLUDE_DIRECTORIES "${CMAKE_CURRENT_LIST_DIR}/dawn-headers/include/webgpu_upstream;${_wasi_webgpu}")
          EOF

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

      # llama-common does not build for WASI, so the executables are linked by hand
      - name: Build
        id: cmake_build
        run: |
          WASI_FLAGS="-msimd128 -D_WASI_EMULATED_SIGNAL -fwasm-exceptions -mllvm -wasm-use-legacy-eh=false"
          cmake -B build-wasi \
            -G "Ninja" \
            -DCMAKE_TOOLCHAIN_FILE=${WASI_SDK_PATH}/share/cmake/wasi-sdk-p3.cmake \
            -DCMAKE_BUILD_TYPE=Release \
            -DCMAKE_C_FLAGS="${WASI_FLAGS}" \
            -DCMAKE_CXX_FLAGS="${WASI_FLAGS}" \
            -DCMAKE_HAVE_LIBC_PTHREAD=1 \
            -DBUILD_SHARED_LIBS=OFF \
            -DGGML_NATIVE=OFF \
            -DGGML_OPENMP=OFF \
            -DGGML_WEBGPU=ON \
            -DDawn_DIR=$PWD/wasi-webgpu \
            -DLLAMA_BUILD_COMMON=OFF

          time cmake --build build-wasi --config Release --target llama -j $(nproc)

          LIBS="build-wasi/ggml/src/libggml.a build-wasi/ggml/src/ggml-webgpu/libggml-webgpu.a build-wasi/ggml/src/libggml-cpu.a build-wasi/ggml/src/libggml-base.a"
          LDFLAGS="-lunwind -ldl -Wl,-z,stack-size=8388608"
          CXX="${WASI_SDK_PATH}/bin/clang++ --target=wasm32-wasip3 -O3 -std=c++17 ${WASI_FLAGS} -I include -I ggml/include"

          $CXX examples/simple/simple.cpp build-wasi/src/libllama.a $LIBS $LDFLAGS -o build-wasi/llama-simple.wasm
          $CXX tests/test-backend-ops.cpp $LIBS $LDFLAGS -o build-wasi/test-backend-ops.wasm

      - 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-arm-wasi
          folder: llama.cpp
          evict-old-files: 1d
          hf_bucket: ggml-org/cache
          save: true