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

name: Server

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.yml',
      '**/CMakeLists.txt',
      '**/Makefile',
      '**/*.h',
      '**/*.hpp',
      '**/*.c',
      '**/*.cpp',
      '**/*.cu',
      '**/*.swift',
      '**/*.m',
      'tools/server/**.*'
    ]
  pull_request:
    types: [opened, synchronize, reopened]
    paths: [
      '.github/workflows/server.yml',
      '**/CMakeLists.txt',
      '**/Makefile',
      '**/*.h',
      '**/*.hpp',
      '**/*.c',
      '**/*.cpp',
      '**/*.cu',
      '**/*.swift',
      '**/*.m',
      'tools/server/**.*'
    ]

env:
  LLAMA_LOG_COLORS: 1
  LLAMA_LOG_PREFIX: 1
  LLAMA_LOG_TIMESTAMPS: 1
  LLAMA_LOG_VERBOSITY: 10

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

jobs:
  webui-build:
    name: Build WebUI
    uses: ./.github/workflows/webui-build.yml

  server:
    needs: webui-build
    runs-on: ubuntu-latest

    name: server (${{ matrix.wf_name }})
    strategy:
      matrix:
        build_type: [Release]
        wf_name: ["default"]
        include:
          - build_type: Release
            extra_args: ""
            wf_name:    "default"
          - build_type: Release
            extra_args: "LLAMA_ARG_BACKEND_SAMPLING=1"
            wf_name:    "backend-sampling"
      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: Download WebUI build artifact
        uses: actions/download-artifact@v7
        with:
          name: webui-build
          path: tools/server/public/

      - name: Build
        id: cmake_build
        run: |
          cmake -B build \
            -DLLAMA_BUILD_BORINGSSL=ON \
            -DGGML_SCHED_NO_REALLOC=ON
          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

  server-windows:
    needs: webui-build
    runs-on: windows-2022

    steps:
      - 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: Download WebUI build artifact
        uses: actions/download-artifact@v7
        with:
          name: webui-build
          path: tools/server/public/

      - name: Build
        id: cmake_build
        run: |
          cmake -B build -DLLAMA_BUILD_BORINGSSL=ON -DGGML_SCHED_NO_REALLOC=ON
          cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS} --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
          $env:PYTHONIOENCODING = ":replace"
          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
          $env:SLOW_TESTS = "1"
          pytest -v -x