llama.cpp/.github/workflows/server.yml at 63e66fdd23eda3a2659a7af9ff6ef15d71efbff1 · CrazyForks/llama.cpp · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
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_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:
  ubuntu:
    runs-on: ubuntu-24.04-arm

    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: ccache
        uses: ggml-org/ccache-action@v1.2.21
        with:
          key: server-ubuntu-24.04-arm
          evict-old-files: 1d
          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}

      - name: Build
        id: cmake_build
        run: |
          cmake -B build \
            -DGGML_SCHED_NO_REALLOC=ON
          cmake --build build --config Release -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
        run: |
          cd tools/server/tests
          pytest -v -x -m "not slow"

      - name: Slow tests
        id: server_integration_tests_slow
        if: ${{ github.event.schedule || github.event.inputs.slow_tests == 'true' }}
        run: |
          cd tools/server/tests
          SLOW_TESTS=1 pytest -v -x

      - name: Tests (Backend sampling)
        id: server_integration_tests_backend_sampling
        run: |
          cd tools/server/tests
          export LLAMA_ARG_BACKEND_SAMPLING=1
          pytest -v -x -m "not slow"

      - name: Slow tests (Backend sampling)
        id: server_integration_tests_slow_backend_sampling
        if: ${{ github.event.schedule || github.event.inputs.slow_tests == 'true' }}
        run: |
          cd tools/server/tests
          export LLAMA_ARG_BACKEND_SAMPLING=1
          SLOW_TESTS=1 pytest -v -x

  windows:
    runs-on: windows-2025

    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: ccache
        uses: ggml-org/ccache-action@v1.2.21
        with:
          key: server-windows-2025-x64
          evict-old-files: 1d
          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}

      - name: Build
        id: cmake_build
        shell: cmd
        run: |
          cmake -B build -G "Ninja Multi-Config" ^
            -DCMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake ^
            -DCMAKE_BUILD_TYPE=Release ^
            -DLLAMA_BUILD_BORINGSSL=ON ^
            -DGGML_SCHED_NO_REALLOC=ON
          set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
          cmake --build build --config Release -j %NINJA_JOBS% --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
        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' }}
        run: |
          cd tools/server/tests
          $env:SLOW_TESTS = "1"
          pytest -v -x