# Nightly CUDA tests. One job per runner_config, running that machine's
# `nightly-test-{runner_config}` suite -- a test reaches a machine by declaring
# `runner_config=` on register_cuda_ci, never by editing this file.
#
# Jobs go through the same _pr-test-stage.yml as the per-commit suites; what a
# scheduled run needs on top is its `scheduled` input, so runner resolution,
# rust-ext reuse and shard sizing are not reimplemented here.
name: Nightly Test (Nvidia)

on:
  schedule:
    - cron: '0 14 */2 * *'
  workflow_dispatch:
    inputs:
      runner_filter:
        description: 'Select which runner_config to run (leave empty or "all" to run all)'
        required: false
        type: choice
        default: 'all'
        options:
          - 'all'
          - '1-gpu-large'
          - '2-gpu-large'
          - '4-gpu-h100'
          - '4-gpu-b200'
          - '4-gpu-gb300'
          - '8-gpu-h200'
          - '8-gpu-b200'
          - 'diffusion'
      full_parallel:
        description: 'Run all shards of a job at once (faster, but competes with per-commit CI for machines). Off by default: one shard at a time.'
        required: false
        type: boolean
        default: false
      force_baseline_update:
        description: 'Refresh the precision rolling baseline instead of comparing. Dispatch once after an intentional forward-path precision change stales it; later runs compare against the new one.'
        required: false
        type: boolean
        default: false
  workflow_call:
    inputs:
      ref:
        description: 'Git ref (branch, tag, or SHA) to test. If not provided, uses the default branch.'
        required: false
        type: string
        default: ''
      runner_filter:
        description: 'Select which runner_config to run (leave empty or "all" to run all)'
        required: false
        type: string
        default: 'all'
      full_parallel:
        description: 'Run all shards of a job at once (faster, but competes with per-commit CI for machines). Off by default: one shard at a time.'
        required: false
        type: boolean
        default: false

concurrency:
  group: nightly-test-nvidia-${{ inputs.ref || github.ref }}
  cancel-in-progress: ${{ github.event_name != 'workflow_call' }}

permissions:
  actions: write
  contents: read
  issues: read
  pull-requests: read

jobs:
  # run_all_tests skips the paths-filter, so main_package is 'true' and
  # sgl_kernel stays empty: every test runs, and no job waits on a wheel this
  # workflow never builds. pr_test_yml points back here so shard sizing reads
  # this file's own run_timeout_minutes.
  check-changes:
    uses: ./.github/workflows/_pr-test-check-changes.yml
    with:
      git_ref: ${{ inputs.ref || '' }}
      pr_test_yml: '.github/workflows/nightly-test-nvidia.yml'
      run_all_tests: true
      force_continue_on_error: true
    secrets: inherit

  nightly-1-gpu-large:
    needs: check-changes
    if: github.repository == 'sgl-project/sglang' && (inputs.runner_filter == '' || inputs.runner_filter == 'all' || inputs.runner_filter == '1-gpu-large')
    uses: ./.github/workflows/_pr-test-stage.yml
    with:
      self_name: nightly-test-1-gpu-large
      runner_config: 1-gpu-large
      check_changes: ${{ toJson(needs.check-changes.outputs) }}
      caller_inputs: ${{ toJson(inputs) }}
      partitions: ${{ needs.check-changes.outputs.partitions }}
      run_timeout_minutes: '120'
      job_timeout_minutes: '180'
      scheduled: true
    secrets: inherit

  nightly-2-gpu-large:
    needs: check-changes
    if: github.repository == 'sgl-project/sglang' && (inputs.runner_filter == '' || inputs.runner_filter == 'all' || inputs.runner_filter == '2-gpu-large')
    uses: ./.github/workflows/_pr-test-stage.yml
    with:
      self_name: nightly-test-2-gpu-large
      runner_config: 2-gpu-large
      check_changes: ${{ toJson(needs.check-changes.outputs) }}
      caller_inputs: ${{ toJson(inputs) }}
      partitions: ${{ needs.check-changes.outputs.partitions }}
      run_timeout_minutes: '240'
      job_timeout_minutes: '300'
      scheduled: true
    secrets: inherit

  nightly-4-gpu-h100:
    needs: check-changes
    if: github.repository == 'sgl-project/sglang' && (inputs.runner_filter == '' || inputs.runner_filter == 'all' || inputs.runner_filter == '4-gpu-h100')
    uses: ./.github/workflows/_pr-test-stage.yml
    with:
      self_name: nightly-test-4-gpu-h100
      runner_config: 4-gpu-h100
      check_changes: ${{ toJson(needs.check-changes.outputs) }}
      caller_inputs: ${{ toJson(inputs) }}
      partitions: ${{ needs.check-changes.outputs.partitions }}
      run_timeout_minutes: '120'
      job_timeout_minutes: '180'
      scheduled: true
    secrets: inherit

  nightly-4-gpu-b200:
    needs: check-changes
    if: github.repository == 'sgl-project/sglang' && (inputs.runner_filter == '' || inputs.runner_filter == 'all' || inputs.runner_filter == '4-gpu-b200')
    uses: ./.github/workflows/_pr-test-stage.yml
    with:
      self_name: nightly-test-4-gpu-b200
      runner_config: 4-gpu-b200
      check_changes: ${{ toJson(needs.check-changes.outputs) }}
      caller_inputs: ${{ toJson(inputs) }}
      partitions: ${{ needs.check-changes.outputs.partitions }}
      run_timeout_minutes: '150'
      job_timeout_minutes: '210'
      scheduled: true
    secrets: inherit

  nightly-4-gpu-gb300:
    needs: check-changes
    if: github.repository == 'sgl-project/sglang' && (inputs.runner_filter == '' || inputs.runner_filter == 'all' || inputs.runner_filter == '4-gpu-gb300')
    uses: ./.github/workflows/_pr-test-stage.yml
    with:
      self_name: nightly-test-4-gpu-gb300
      runner_config: 4-gpu-gb300
      check_changes: ${{ toJson(needs.check-changes.outputs) }}
      caller_inputs: ${{ toJson(inputs) }}
      partitions: ${{ needs.check-changes.outputs.partitions }}
      run_timeout_minutes: '360'
      job_timeout_minutes: '420'
      scheduled: true
    secrets: inherit

  nightly-8-gpu-h200:
    needs: check-changes
    if: github.repository == 'sgl-project/sglang' && (inputs.runner_filter == '' || inputs.runner_filter == 'all' || inputs.runner_filter == '8-gpu-h200')
    uses: ./.github/workflows/_pr-test-stage.yml
    with:
      self_name: nightly-test-8-gpu-h200
      runner_config: 8-gpu-h200
      check_changes: ${{ toJson(needs.check-changes.outputs) }}
      caller_inputs: ${{ toJson(inputs) }}
      partitions: ${{ needs.check-changes.outputs.partitions }}
      run_timeout_minutes: '300'
      job_timeout_minutes: '360'
      scheduled: true
    secrets: inherit

  nightly-8-gpu-b200:
    needs: check-changes
    if: github.repository == 'sgl-project/sglang' && (inputs.runner_filter == '' || inputs.runner_filter == 'all' || inputs.runner_filter == '8-gpu-b200')
    uses: ./.github/workflows/_pr-test-stage.yml
    with:
      self_name: nightly-test-8-gpu-b200
      runner_config: 8-gpu-b200
      check_changes: ${{ toJson(needs.check-changes.outputs) }}
      caller_inputs: ${{ toJson(inputs) }}
      partitions: ${{ needs.check-changes.outputs.partitions }}
      run_timeout_minutes: '360'
      job_timeout_minutes: '420'
      scheduled: true
    secrets: inherit

  # Hand-written because it is not a registry suite: it drives run_comparison.py
  # and publishes a dashboard rather than running test files.
  nightly-test-diffusion:
    if: github.repository == 'sgl-project/sglang' && (inputs.runner_filter == '' || inputs.runner_filter == 'all' || inputs.runner_filter == 'diffusion')
    runs-on: 4-gpu-h100
    timeout-minutes: 300
    env:
      SGLANG_IS_IN_CI: true
      SGLANG_ENABLE_ASYNC_ASSERT: true
      SGLANG_CUDA_COREDUMP: "1"
      HF_HUB_DOWNLOAD_TIMEOUT: 300
      HF_HUB_ETAG_TIMEOUT: 300
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
        with:
          ref: ${{ inputs.ref || github.sha }}

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

      - name: Run diffusion benchmark
        env:
          GITHUB_SHA: ${{ github.sha }}
          GITHUB_RUN_ID: ${{ github.run_id }}
          PYTHONUNBUFFERED: "1"
        timeout-minutes: 210
        run: |
          python3 -u scripts/ci/utils/diffusion/run_comparison.py \
            --output comparison-results.json

      - name: Generate dashboard
        if: always()
        env:
          GH_PAT_FOR_NIGHTLY_CI_DATA: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
          GH_TOKEN: ${{ github.token }}
        run: |
          python3 scripts/ci/utils/diffusion/generate_diffusion_dashboard.py \
            --results comparison-results.json \
            --output dashboard.md \
            --charts-dir comparison-charts \
            --fetch-history \
            --step-summary

      - name: Publish to sglang-ci-data
        if: always()
        env:
          GH_PAT_FOR_NIGHTLY_CI_DATA: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
        run: |
          python3 scripts/ci/utils/diffusion/publish_comparison_results.py \
            --results comparison-results.json \
            --dashboard dashboard.md \
            --charts-dir comparison-charts

      - name: Upload benchmark artifacts
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: diffusion-benchmark-${{ github.run_id }}
          path: |
            comparison-results.json
            dashboard.md
            comparison-charts/
            comparison-logs/
          retention-days: 90
          if-no-files-found: ignore

      - uses: ./.github/actions/upload-cuda-coredumps
        if: failure()

  # Consolidate performance metrics from all jobs
  consolidate-metrics:
    if: github.repository == 'sgl-project/sglang' && always()
    # Every scheduled stage uploads metrics now, so all of them must finish
    # before the download step globs `*metrics-*`.
    needs:
      - nightly-1-gpu-large
      - nightly-2-gpu-large
      - nightly-4-gpu-h100
      - nightly-4-gpu-b200
      - nightly-4-gpu-gb300
      - nightly-8-gpu-h200
      - nightly-8-gpu-b200
    runs-on: ubuntu-latest
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
        with:
          ref: ${{ inputs.ref || github.ref }}

      - name: Download all partition metrics
        uses: actions/download-artifact@v4
        with:
          pattern: "*metrics-*"
          path: metrics/
          merge-multiple: true

      - name: List downloaded metrics
        run: |
          echo "Downloaded metrics files:"
          find metrics/ -name "*.json" -type f 2>/dev/null || echo "No metrics files found"

      - name: Merge metrics
        run: |
          python3 scripts/ci/utils/merge_metrics.py \
            --input-dir metrics/ \
            --output consolidated-metrics-${{ github.run_id }}.json \
            --run-id ${{ github.run_id }} \
            --commit-sha ${{ github.sha }} \
            --branch ${{ github.ref_name }}

      - name: Upload consolidated metrics
        uses: actions/upload-artifact@v4
        with:
          name: consolidated-metrics-${{ github.run_id }}
          path: consolidated-metrics-${{ github.run_id }}.json
          retention-days: 90
          if-no-files-found: warn

  # Final check job
  check-all-jobs:
    if: github.repository == 'sgl-project/sglang' && always()
    needs:
      - nightly-1-gpu-large
      - nightly-2-gpu-large
      - nightly-4-gpu-h100
      - nightly-4-gpu-b200
      - nightly-4-gpu-gb300
      - nightly-8-gpu-h200
      - nightly-8-gpu-b200
      - nightly-test-diffusion
      - consolidate-metrics
    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"