name: Nightly Test B200

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-4-gpu-b200:
    if: github.repository == 'sgl-project/sglang'
    runs-on: 4-gpu-b200

    env:
      RUNNER_LABELS: 4-gpu-b200
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Install dependencies
        run: |
          IS_BLACKWELL=1 bash scripts/ci/ci_install_dependency.sh

      - name: Run GPT-OSS 4GPU nightly performance test
        timeout-minutes: 60
        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: |
          rm -rf test/srt/performance_profiles_gpt_oss_4gpu/
          cd test/srt
          python3 nightly/test_gpt_oss_4gpu_perf.py

      - name: Publish GPT-OSS 4GPU 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_gpt_oss_4gpu

  nightly-test-8-gpu-b200:
    if: github.repository == 'sgl-project/sglang'
    runs-on: 8-gpu-b200
    env:
      RUNNER_LABELS: 8-gpu-b200
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Install dependencies
        run: |
          IS_BLACKWELL=1 bash scripts/ci/ci_install_dependency.sh

      - name: Run DeepSeek v3.1 nightly performance test
        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: |
          rm -rf test/srt/performance_profiles_deepseek_v31/
          cd test/srt
          IS_BLACKWELL=1 python3 nightly/test_deepseek_v31_perf.py

      - name: Publish DeepSeek v3.1 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_deepseek_v31

      - name: Run DeepSeek v3.2 nightly performance test
        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: |
          rm -rf test/srt/performance_profiles_deepseek_v32/
          cd test/srt
          IS_BLACKWELL=1 python3 nightly/test_deepseek_v32_perf.py

      - name: Publish DeepSeek v3.2 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_deepseek_v32

  check-all-jobs:
    if: always() && (github.repository == 'sgl-project/sglang' || github.event_name == 'workflow_dispatch')
    needs:
      - nightly-test-4-gpu-b200
      - nightly-test-8-gpu-b200
    runs-on: ubuntu-latest
    steps:
      - name: Check if any job failed
        run: |
          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"