backend/llama.cpp/.github/workflows/server-sanitize.yml

name: Server (sanitize)

on:
  workflow_dispatch: # allows manual triggering
    inputs:
      sha:
        description: 'Commit SHA1 to build'
        required: false
        type: string
      slow_tests:
        description: 'Run slow tests'
        required: true
        type: boolean
  push:
    branches:
      - master
    paths: [
      '.github/workflows/server-sanitize.yml',
      '**/CMakeLists.txt',
      '**/Makefile',
      '**/*.h',
      '**/*.hpp',
      '**/*.c',
      '**/*.cpp',
      'tools/server/**.*'
    ]

env:
  LLAMA_ARG_LOG_COLORS: 1
  LLAMA_ARG_LOG_PREFIX: 1
  LLAMA_ARG_LOG_TIMESTAMPS: 1
  LLAMA_ARG_LOG_VERBOSITY: 10

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

jobs:
  server:
    runs-on: [self-hosted, CPU, Linux, llama-server]

    strategy:
      matrix:
        sanitizer: [ADDRESS, UNDEFINED] # THREAD is very slow
        build_type: [RelWithDebInfo]
      fail-fast: false

    steps:
      #- name: Dependencies
      #  id: depends
      #  run: |
      #    sudo apt-get update
      #    sudo apt-get -y install \
      #      build-essential \
      #      xxd \
      #      git \
      #      cmake \
      #      curl \
      #      wget \
      #      language-pack-en \
      #      libssl-dev

      - name: Clone
        id: checkout
        uses: actions/checkout@v6
        with:
          fetch-depth: 0
          ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}

      - name: Setup Node.js
        uses: actions/setup-node@v6
        with:
          node-version: "24"
          cache: "npm"
          cache-dependency-path: "tools/ui/package-lock.json"

      - name: Build
        id: cmake_build
        run: |
          cmake -B build \
            -DLLAMA_BUILD_BORINGSSL=ON \
            -DGGML_SCHED_NO_REALLOC=ON \
            -DGGML_SANITIZE_ADDRESS=${{ matrix.sanitizer == 'ADDRESS' }} \
            -DGGML_SANITIZE_THREAD=${{ matrix.sanitizer == 'THREAD' }} \
            -DGGML_SANITIZE_UNDEFINED=${{ matrix.sanitizer == 'UNDEFINED' }} \
            -DLLAMA_SANITIZE_ADDRESS=${{ matrix.sanitizer == 'ADDRESS' }} \
            -DLLAMA_SANITIZE_THREAD=${{ matrix.sanitizer == 'THREAD' }} \
            -DLLAMA_SANITIZE_UNDEFINED=${{ matrix.sanitizer == 'UNDEFINED' }}
          cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server

      - name: Python setup
        id: setup_python
        uses: actions/setup-python@v6
        with:
          python-version: '3.11'
          pip-install: -r tools/server/tests/requirements.txt

      - name: Tests
        id: server_integration_tests
        if: ${{ (!matrix.disabled_on_pr || !github.event.pull_request) }}
        run: |
          cd tools/server/tests
          export ${{ matrix.extra_args }}
          pytest -v -x -m "not slow"

      - name: Slow tests
        id: server_integration_tests_slow
        if: ${{ (github.event.schedule || github.event.inputs.slow_tests == 'true') && matrix.build_type == 'Release' }}
        run: |
          cd tools/server/tests
          export ${{ matrix.extra_args }}
          SLOW_TESTS=1 pytest -v -x