name: Fusion

on:
  workflow_dispatch: # allows manual triggering
  push:
    branches:
      - master
    paths: [
      '.github/workflows/fusion.yml',
      'ggml/**',
      'tests/fusion/**',
      'tests/test-fusion.cpp',
      'tests/test-llama-archs.cpp',
      'src/models/**'
    ]

  pull_request:
    types: [opened, synchronize, reopened]
    paths: [
      '.github/workflows/fusion.yml',
      'ggml/**',
      'tests/fusion/**',
      'tests/test-fusion.cpp',
      'tests/test-llama-archs.cpp',
      'src/models/**'
    ]

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:
  # TODO: add jobs for other backends as they adopt the fusion debug API
  metal:
    runs-on: [self-hosted, macOS, ARM64]

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

      - name: Build
        id: cmake_build
        run: |
          cmake -B build \
            -DCMAKE_BUILD_TYPE=Release \
            -DLLAMA_FATAL_WARNINGS=ON \
            -DLLAMA_OPENSSL=OFF \
            -DGGML_SCHED_NO_REALLOC=ON \
            -DGGML_BLAS=OFF \
            -DGGML_METAL=ON
          time cmake --build build --config Release --target test-llama-archs -j $(sysctl -n hw.logicalcpu)
          time cmake --build build --config Release --target test-fusion -j $(sysctl -n hw.logicalcpu)

      - name: Generate models
        id: generate_models
        run: |
          rm -rf build-ci-models && mkdir -p build-ci-models
          ./build/bin/test-llama-archs -o build-ci-models

      - name: Test fusion
        id: test_fusion
        run: |
          ./build/bin/test-fusion --models build-ci-models --device MTL0 --check tests/fusion/MTL.csv