Model-Optimizer/.github/workflows/gpu_tests.yml at main · NVIDIA/Model-Optimizer · 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
name: GPU tests

on:
  push:
    branches: ["pull-request/[0-9]+"]
    # NOTE: paths cannot be used since push happens to copied PR and only latest commit to PR is used
  schedule:
    - cron: "0 0 * * *" # Nightly
  workflow_dispatch:
    # On-demand


concurrency:
  # Cancel previous runs if new commit is pushed to the same PR
  group: ${{ github.workflow }}-${{ startsWith(github.ref, 'refs/heads/pull-request/') && github.ref || github.sha }}
  cancel-in-progress: true

jobs:
  pr-gate:
    uses: ./.github/workflows/_pr_gate.yml
    permissions:
      checks: read
    secrets: inherit
    with:
      files: |
        .github/workflows/gpu_tests.yml
        modelopt/**
        noxfile.py
        pyproject.toml
        tests/gpu/**
        tests/gpu_megatron/**
        tests/gpu_trtllm/**

  gpu-tests:
    needs: [pr-gate]
    if: needs.pr-gate.outputs.any_changed == 'true'
    strategy:
      fail-fast: false
      matrix:
        include:
          - example: gpu
            timeout: 60
            container_image: pytorch:26.01-py3
            # tests/gpu/_extensions/test_onnx_extensions.py fails for newer containers until https://github.com/tbenthompson/cppimport/pull/98
          - example: gpu_megatron
            timeout: 45
            container_image: nemo:26.04
          - example: gpu_trtllm
            timeout: 30
            container_image: tensorrt-llm/release:1.3.0rc10
    runs-on: ${{ startsWith(github.ref, 'refs/heads/pull-request/') && 'linux-amd64-gpu-rtxpro6000-latest-1' || 'linux-amd64-gpu-rtxpro6000-latest-2' }}
    timeout-minutes: ${{ matrix.timeout }}
    container:
      image: nvcr.io/nvidia/${{ matrix.container_image }}
      env:
        GIT_DEPTH: 1000 # For correct version
        PIP_CONSTRAINT: "" # Disable pip constraint for upgrading packages
        HF_TOKEN: ${{ secrets.HF_TOKEN }}
    steps:
      - uses: actions/checkout@v6
      - uses: nv-gha-runners/setup-proxy-cache@main
      - name: Setup environment variables
        run: |
          echo "LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/include:/usr/lib/x86_64-linux-gnu" >> $GITHUB_ENV
      - name: Run gpu tests
        env:
          COVERAGE_PROCESS_START: ${{ github.workspace }}/pyproject.toml
          COVERAGE_FILE: ${{ github.workspace }}/.coverage
        run: |
          python -m pip install nox && nox -s ${{ matrix.example }}
      - name: Upload GPU coverage to Codecov
        uses: codecov/codecov-action@v5
        with:
          token: ${{ secrets.CODECOV_TOKEN }}
          files: coverage.xml
          flags: gpu
          fail_ci_if_error: false # test may be skipped if relevant file changes are not detected
          verbose: true

  gpu-pr-required-check:
    # Run even if gpu-tests is skipped
    if: ${{ startsWith(github.ref, 'refs/heads/pull-request/') && always() }}
    needs: [pr-gate, gpu-tests]
    runs-on: ubuntu-latest
    steps:
      - name: Required GPU tests did not succeed
        if: ${{ needs.pr-gate.result != 'success' || (needs.pr-gate.outputs.any_changed == 'true' && needs.gpu-tests.result != 'success') }}
        run: exit 1