llama.cpp/.github/workflows/behavior-check.yml at master · Distillative-AI/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
name: Behavior Check

on:
  workflow_dispatch: # allows manual triggering
  push:
    branches:
      - master
    paths: [
      '.github/workflows/behavior-check.yml',
      '**/CMakeLists.txt',
      '**/.cmake',
      '**/*.h',
      '**/*.hpp',
      '**/*.c',
      '**/*.cpp',
    ]

  pull_request:
    types: [opened, synchronize, reopened]
    paths: [
      '.github/workflows/behavior-check.yml',
      '**/CMakeLists.txt',
      '**/.cmake',
      '**/*.h',
      '**/*.hpp',
      '**/*.c',
      '**/*.cpp'
    ]

cache-mode: none
permissions:
  contents: read

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

env:
  GGML_NLOOP: 3
  GGML_N_THREADS: 1
  GGML_SCHED_DEBUG_REALLOC: 1
  LLAMA_ARG_LOG_COLORS: 1
  LLAMA_ARG_LOG_PREFIX: 1
  LLAMA_ARG_LOG_TIMESTAMPS: 1

jobs:
  ubuntu:
    runs-on: ubuntu-26.04-arm

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

      - name: ccache
        uses: ggml-org/ccache-action@v1.2.24
        with:
          restore: false
          save: false

      - name: Build Dependencies
        id: build_depends
        run: |
          sudo apt update
          sudo apt install -y build-essential libssl-dev git-lfs libjpeg-dev python3 python3-venv python3-pip

      - name: Python Dependencies
        id: python_depends
        run: |
          python3 -m venv .venv
          source .venv/bin/activate
          pip install jinja2==3.1.6

      - name: ccache-buckets-restore
        uses: ./.github/actions/ccache-buckets
        env:
          HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
        with:
          key: behavior-check-ubuntu-26.04-arm
          folder: llama.cpp
          hf_bucket: ggml-org/cache

      - name: Build
        id: cmake_build
        run: |
          cmake -B build \
            -DGGML_NATIVE=OFF \
            -DGGML_BACKEND_DL=OFF \
            -DLLAMA_FATAL_WARNINGS=ON
          time cmake --build build --config Release -j $(nproc)

      - name: ccache-buckets-save
        if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
        uses: ./.github/actions/ccache-buckets
        env:
          HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
        with:
          key: behavior-check-ubuntu-26.04-arm
          folder: llama.cpp
          evict-old-files: 1d
          hf_bucket: ggml-org/cache
          save: true

      - name: Test
        id: cmake_test
        run: |
          source .venv/bin/activate
          cd build
          ctest -L behavior -LE 'model|backend' --verbose --timeout 900