name: Nightly Test

on:
  schedule:
    - cron: '0 0 * * *'
  push:
    branches:
      - main
    paths:
      - "python/sglang/version.py"
  workflow_dispatch:

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

jobs:
  nightly-test-eval-text-models:
    if: github.repository == 'sgl-project/sglang'
    runs-on: 2-gpu-runner
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

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

      - name: Run eval test for text models
        timeout-minutes: 120
        run: |
          cd test/srt
          python3 nightly/test_text_models_gsm8k_eval.py

  nightly-test-perf-text-models:
    if: github.repository == 'sgl-project/sglang'
    runs-on: 2-gpu-runner
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

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

      - name: Run performance test for text models
        timeout-minutes: 180
        env:
          TRACE_BASE_URL: https://raw.githubusercontent.com/sglang-bot/sglang-ci-data/main/traces/${{ github.run_id }}
          PERFETTO_RELAY_URL: ${{ vars.PERFETTO_RELAY_URL }}
        run: |
          cd test/srt
          rm -rf performance_profiles_text_models/
          python3 nightly/test_text_models_perf.py

      - name: Publish traces to storage repo
        env:
          GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
          GITHUB_RUN_ID: ${{ github.run_id }}
          GITHUB_RUN_NUMBER: ${{ github.run_number }}
        run: |
          python3 scripts/ci/publish_traces.py --traces-dir test/srt/performance_profiles_text_models

  nightly-test-eval-vlms:
    if: github.repository == 'sgl-project/sglang'
    runs-on: 2-gpu-runner
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

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

      - name: Run eval test for VLM models (fixed MMMU-100)
        timeout-minutes: 240
        run: |
          cd test/srt
          python3 nightly/test_vlms_mmmu_eval.py

  nightly-test-perf-vlms:
    if: github.repository == 'sgl-project/sglang'
    runs-on: 2-gpu-runner
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

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

      - name: Run perf test for VLM models (MMMU)
        timeout-minutes: 240
        env:
          TRACE_BASE_URL: https://raw.githubusercontent.com/sglang-bot/sglang-ci-data/main/traces/${{ github.run_id }}
          PERFETTO_RELAY_URL: ${{ vars.PERFETTO_RELAY_URL }}
        run: |
          cd test/srt
          rm -rf performance_profiles_vlms/
          python3 nightly/test_vlms_perf.py

      - name: Publish traces to storage repo
        env:
          GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
          GITHUB_RUN_ID: ${{ github.run_id }}
          GITHUB_RUN_NUMBER: ${{ github.run_number }}
        run: |
          python3 scripts/ci/publish_traces.py --traces-dir test/srt/performance_profiles_vlms

  nightly-test-1-gpu:
    if: github.repository == 'sgl-project/sglang'
    runs-on: 1-gpu-runner

    env:
      RUNNER_LABELS: 1-gpu-runner
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

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

      - name: Run test
        timeout-minutes: 60
        run: |
          cd test/srt
          python3 run_suite.py --suite nightly-1-gpu --continue-on-error

  nightly-test-4-gpu:
    if: github.repository == 'sgl-project/sglang'
    runs-on: 4-gpu-h100
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

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

      - name: Run test
        timeout-minutes: 30
        run: |
          cd test/srt
          python3 run_suite.py --suite nightly-4-gpu --continue-on-error

  nightly-test-8-gpu-h200:
    if: github.repository == 'sgl-project/sglang'
    runs-on: 8-gpu-h200
    env:
      RUNNER_LABELS: 8-gpu-h200
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

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

      - name: Run test
        timeout-minutes: 30
        run: |
          cd test/srt
          python3 run_suite.py --suite nightly-8-gpu-h200 --continue-on-error

  nightly-test-8-gpu-h20:
    if: github.repository == 'sgl-project/sglang'
    runs-on: 8-gpu-h20
    env:
      SGLANG_CI_RDMA_ALL_DEVICES: "mlx5_1,mlx5_2,mlx5_3,mlx5_4"
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

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

      - name: Run test
        timeout-minutes: 30
        run: |
          cd test/srt
          python3 run_suite.py --suite nightly-8-gpu-h20 --continue-on-error

  check-all-jobs:
    if: always() && (github.repository == 'sgl-project/sglang' || github.event_name == 'workflow_dispatch')
    needs:
      - nightly-test-eval-text-models
      - nightly-test-perf-text-models
      - nightly-test-eval-vlms
      - nightly-test-perf-vlms
      - nightly-test-1-gpu
      - nightly-test-4-gpu
      - nightly-test-8-gpu-h200
      - nightly-test-8-gpu-h20
    runs-on: ubuntu-latest
    steps:
      - name: Check if any job failed
        run: |
          # Now that continue-on-error is removed, failures will be properly reported
          if [[ "${{ contains(needs.*.result, 'failure') }}" == "true" ]]; then
            echo "One or more nightly test jobs failed"
            exit 1
          fi
          if [[ "${{ contains(needs.*.result, 'cancelled') }}" == "true" ]]; then
            echo "One or more nightly test jobs were cancelled"
            exit 1
          fi
          echo "All nightly test jobs passed"