llama.cpp/.github/workflows/server.yml

# Server build and tests
name: Server

on:
  workflow_dispatch: # allows manual triggering
    inputs:
      slow_tests:
        description: 'Run slow tests'
        required: true
        type: boolean
  push:
    branches:
      - master
    paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'examples/server/tests/**.*']
  pull_request:
    types: [opened, synchronize, reopened]
    paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'examples/server/tests/**.*']
  schedule:
    -  cron: '0 0 * * *'

jobs:
  server:
    runs-on: ubuntu-latest

    strategy:
      matrix:
        sanitizer: [ADDRESS, THREAD, UNDEFINED]
        build_type: [Debug]
        include:
          - build_type: Release
            sanitizer: ""
          - build_type: Debug
            sanitizer: THREAD
            disabled_on_pr: true
      fail-fast: false # While -DLLAMA_SANITIZE_THREAD=ON is broken

    container:
      image: ubuntu:latest
      ports:
        - 8888
      options: --cpus 4

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v3
        with:
          fetch-depth: 0

      - name: Dependencies
        id: depends
        run: |
          apt-get update
          apt-get -y install \
            build-essential \
            git \
            cmake \
            python3-pip \
            wget \
            language-pack-en

      - name: Build
        id: cmake_build
        run: |
          mkdir build
          cd build
          cmake .. \
              -DLLAMA_NATIVE=OFF \
              -DLLAMA_BUILD_SERVER=ON \
              -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
              -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON ;
          cmake --build . --config ${{ matrix.build_type }} -j $(nproc) --target server

      - name: Tests dependencies
        id: test_dependencies
        run: |
          pip install -r examples/server/tests/requirements.txt

      - name: Tests
        id: server_integration_tests
        if: ${{ !matrix.disabled_on_pr || !github.event.pull_request }}
        run: |
          cd examples/server/tests
          PORT=8888 ./tests.sh

      - name: Slow tests
        id: server_integration_tests_slow
        if: ${{ (github.event.schedule || github.event.inputs.slow_tests == 'true') && matrix.build_type == 'Release' }}
        run: |
          cd examples/server/tests
          PORT=8888 ./tests.sh --stop --no-skipped --no-capture --tags slow


  server-windows:
    runs-on: windows-latest

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v3
        with:
          fetch-depth: 0

      - name: Build
        id: cmake_build
        run: |
          mkdir build
          cd build
          cmake ..  -DLLAMA_BUILD_SERVER=ON -DCMAKE_BUILD_TYPE=Release ;
          cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS} --target server

      - name: Python setup
        id: setup_python
        uses: actions/setup-python@v5
        with:
          python-version: '3.11'

      - name: Tests dependencies
        id: test_dependencies
        run: |
          pip install -r examples/server/tests/requirements.txt

      - name: Tests
        id: server_integration_tests
        if: ${{ !matrix.disabled_on_pr || !github.event.pull_request }}
        run: |
          cd examples/server/tests
          behave.exe --summary --stop --no-capture --exclude 'issues|wrong_usages|passkey' --tags llama.cpp

      - name: Slow tests
        id: server_integration_tests_slow
        if: ${{ (github.event.schedule || github.event.inputs.slow_tests == 'true') && matrix.build_type == 'Release' }}
        run: |
          cd examples/server/tests
          behave.exe --stop --no-skipped --no-capture --tags slow