sgl-project--sglang/.github/workflows/weekly-test-nvidia.yml

name: Weekly Test (Nvidia)

on:
  schedule:
    - cron: '0 0 * * 0'  # Run every Sunday at midnight UTC
  workflow_dispatch:
    inputs:
      job_filter:
        description: 'Select which job to run (leave empty or "all" to run all jobs)'
        required: false
        type: choice
        default: 'all'
        options:
          - 'all'
          - 'weekly-test-8-gpu-h200'

concurrency:
  group: weekly-test-nvidia-${{ github.ref }}
  cancel-in-progress: true

env:
  SGLANG_IS_IN_CI: true
  SGLANG_ENABLE_ASYNC_ASSERT: true
  HF_HUB_DOWNLOAD_TIMEOUT: 300
  HF_HUB_ETAG_TIMEOUT: 300

jobs:
  # Weekly tests - 8 GPU H200
  weekly-test-8-gpu-h200:
    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'weekly-test-8-gpu-h200')
    runs-on: 8-gpu-h200
    timeout-minutes: 120
    env:
      RUNNER_LABELS: 8-gpu-h200
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Install dependencies
        run: |
          bash scripts/ci/cuda/ci_install_dependency.sh

      - name: Run weekly 8-GPU H200 tests
        timeout-minutes: 120
        env:
          GPU_CONFIG: "8-gpu-h200"
          IS_H200: "1"
        run: |
          cd test
          python3 run_suite.py --hw cuda --suite weekly-8-gpu-h200 --nightly --continue-on-error --timeout-per-file 7200