chore: vendor sglang v0.5.10 snapshot

third_party/sglang/.github/workflows/amd-aiter-scout.yml

@@ -0,0 +1,161 @@
+name: AMD AITER Scout
+
+on:
+  schedule:
+    - cron: '0 20 * * 1'   # Monday 20:00 UTC
+    - cron: '0 20 * * 4'   # Thursday 20:00 UTC
+  workflow_dispatch:
+    inputs:
+      aiter_ref:
+        description: 'AITER git ref (branch, tag, or SHA). Default: main (latest commit)'
+        required: false
+        type: string
+        default: 'main'
+      job_filter:
+        description: 'Comma-separated workflows to run: nightly-amd, nightly-amd-rocm720, pr-test-amd, pr-test-amd-rocm720. Default: all'
+        required: false
+        type: string
+        default: 'all'
+      continue_on_error:
+        description: 'Continue running other workflows even if one fails'
+        required: false
+        type: boolean
+        default: true
+
+concurrency:
+  group: amd-aiter-scout-${{ github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  resolve-aiter:
+    runs-on: ubuntu-latest
+    outputs:
+      aiter_sha: ${{ steps.resolve.outputs.sha }}
+      run_nightly_amd: ${{ steps.parse.outputs.run_nightly_amd }}
+      run_nightly_amd_rocm720: ${{ steps.parse.outputs.run_nightly_amd_rocm720 }}
+      run_pr_test_amd: ${{ steps.parse.outputs.run_pr_test_amd }}
+      run_pr_test_amd_rocm720: ${{ steps.parse.outputs.run_pr_test_amd_rocm720 }}
+    steps:
+      - name: Resolve AITER commit
+        id: resolve
+        run: |
+          REF="${{ inputs.aiter_ref || 'main' }}"
+          echo "Resolving AITER ref: ${REF}"
+
+          SHA=$(git ls-remote https://github.com/ROCm/aiter.git "refs/heads/${REF}" | head -1 | cut -f1)
+          if [ -z "$SHA" ]; then
+            SHA=$(git ls-remote https://github.com/ROCm/aiter.git "refs/tags/${REF}" | head -1 | cut -f1)
+          fi
+          if [ -z "$SHA" ]; then
+            SHA=$(git ls-remote https://github.com/ROCm/aiter.git "${REF}" | head -1 | cut -f1)
+          fi
+          if [ -z "$SHA" ]; then
+            SHA="${REF}"
+          fi
+
+          echo "sha=${SHA}" >> $GITHUB_OUTPUT
+          echo "### AITER Ref Resolution" >> $GITHUB_STEP_SUMMARY
+          echo "- **Requested ref:** \`${REF}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- **Resolved SHA:** \`${SHA}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- **AITER commit:** https://github.com/ROCm/aiter/commit/${SHA}" >> $GITHUB_STEP_SUMMARY
+
+      - name: Parse job filter
+        id: parse
+        run: |
+          FILTER="${{ inputs.job_filter || 'all' }}"
+          echo "Job filter: ${FILTER}"
+
+          if [[ "$FILTER" == "all" ]]; then
+            echo "run_nightly_amd=true" >> $GITHUB_OUTPUT
+            echo "run_nightly_amd_rocm720=true" >> $GITHUB_OUTPUT
+            echo "run_pr_test_amd=true" >> $GITHUB_OUTPUT
+            echo "run_pr_test_amd_rocm720=true" >> $GITHUB_OUTPUT
+          else
+            # Wrap with commas for exact substring matching (avoids "nightly-amd" matching "nightly-amd-rocm720")
+            PADDED=",${FILTER// /},"
+            echo "run_nightly_amd=$(echo "$PADDED" | grep -q ',nightly-amd,' && echo true || echo false)" >> $GITHUB_OUTPUT
+            echo "run_nightly_amd_rocm720=$(echo "$PADDED" | grep -q ',nightly-amd-rocm720,' && echo true || echo false)" >> $GITHUB_OUTPUT
+            echo "run_pr_test_amd=$(echo "$PADDED" | grep -q ',pr-test-amd,' && echo true || echo false)" >> $GITHUB_OUTPUT
+            echo "run_pr_test_amd_rocm720=$(echo "$PADDED" | grep -q ',pr-test-amd-rocm720,' && echo true || echo false)" >> $GITHUB_OUTPUT
+          fi
+
+          echo "### Job Filter" >> $GITHUB_STEP_SUMMARY
+          echo "- **Filter:** \`${FILTER}\`" >> $GITHUB_STEP_SUMMARY
+
+  call-nightly-amd:
+    if: needs.resolve-aiter.outputs.run_nightly_amd == 'true'
+    needs: resolve-aiter
+    uses: ./.github/workflows/nightly-test-amd.yml
+    secrets: inherit
+    with:
+      ref: ${{ github.sha }}
+      aiter_ref: ${{ needs.resolve-aiter.outputs.aiter_sha }}
+      job_filter: 'all'
+      continue_on_error: ${{ inputs.continue_on_error == '' && true || inputs.continue_on_error }}
+
+  call-nightly-amd-rocm720:
+    if: needs.resolve-aiter.outputs.run_nightly_amd_rocm720 == 'true'
+    needs: resolve-aiter
+    uses: ./.github/workflows/nightly-test-amd-rocm720.yml
+    secrets: inherit
+    with:
+      ref: ${{ github.sha }}
+      aiter_ref: ${{ needs.resolve-aiter.outputs.aiter_sha }}
+      job_filter: 'all'
+      continue_on_error: ${{ inputs.continue_on_error == '' && true || inputs.continue_on_error }}
+
+  call-pr-test-amd:
+    if: needs.resolve-aiter.outputs.run_pr_test_amd == 'true'
+    needs: resolve-aiter
+    uses: ./.github/workflows/pr-test-amd.yml
+    secrets: inherit
+    with:
+      run_all_tests: true
+      aiter_ref: ${{ needs.resolve-aiter.outputs.aiter_sha }}
+      continue_on_error: ${{ inputs.continue_on_error == '' && true || inputs.continue_on_error }}
+
+  call-pr-test-amd-rocm720:
+    if: needs.resolve-aiter.outputs.run_pr_test_amd_rocm720 == 'true'
+    needs: resolve-aiter
+    uses: ./.github/workflows/pr-test-amd-rocm720.yml
+    secrets: inherit
+    with:
+      run_all_tests: true
+      aiter_ref: ${{ needs.resolve-aiter.outputs.aiter_sha }}
+      continue_on_error: ${{ inputs.continue_on_error == '' && true || inputs.continue_on_error }}
+
+  check-all-jobs:
+    if: always()
+    needs:
+      - resolve-aiter
+      - call-nightly-amd
+      - call-nightly-amd-rocm720
+      - call-pr-test-amd
+      - call-pr-test-amd-rocm720
+    runs-on: ubuntu-latest
+    steps:
+      - name: Summary
+        run: |
+          echo "## AMD AITER Scout Results" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "- **AITER SHA:** \`${{ needs.resolve-aiter.outputs.aiter_sha }}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- **AITER commit:** https://github.com/ROCm/aiter/commit/${{ needs.resolve-aiter.outputs.aiter_sha }}" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "| Workflow | Result |" >> $GITHUB_STEP_SUMMARY
+          echo "|----------|--------|" >> $GITHUB_STEP_SUMMARY
+          echo "| Nightly AMD (AITER Latest) | \`${{ needs.call-nightly-amd.result }}\` |" >> $GITHUB_STEP_SUMMARY
+          echo "| Nightly AMD ROCm 7.2 | \`${{ needs.call-nightly-amd-rocm720.result }}\` |" >> $GITHUB_STEP_SUMMARY
+          echo "| PR Test AMD (AITER Latest) | \`${{ needs.call-pr-test-amd.result }}\` |" >> $GITHUB_STEP_SUMMARY
+          echo "| PR Test AMD ROCm 7.2 | \`${{ needs.call-pr-test-amd-rocm720.result }}\` |" >> $GITHUB_STEP_SUMMARY
+
+      - name: Check if any job failed
+        run: |
+          if [[ "${{ contains(needs.*.result, 'failure') }}" == "true" ]]; then
+            echo "One or more workflows failed"
+            exit 1
+          fi
+          if [[ "${{ contains(needs.*.result, 'cancelled') }}" == "true" ]]; then
+            echo "One or more workflows were cancelled"
+            exit 1
+          fi
+          echo "All workflows passed"

third_party/sglang/.github/workflows/amd-ci-job-monitor.yml

@@ -0,0 +1,338 @@
+name: AMD CI Job Monitor
+
+on:
+  schedule:
+    - cron: '0 0 * * *'  # Daily at midnight UTC
+  pull_request:
+    paths:
+      - '.github/workflows/amd-ci-job-monitor.yml'
+      - 'scripts/ci/utils/query_job_status.py'
+  workflow_dispatch:
+    inputs:
+      hours:
+        description: 'Time window in hours'
+        required: false
+        default: '24'
+        type: string
+      job_filter:
+        description: 'Job name filter (leave empty for all AMD jobs)'
+        required: false
+        type: string
+
+jobs:
+  fetch-actions-data:
+    name: Fetch Actions Snapshot
+    runs-on: ubuntu-latest
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: pip install tabulate
+
+      - name: Select workflows for snapshot
+        id: select-workflows
+        run: |
+          if [[ -n "${{ inputs.job_filter }}" ]]; then
+            echo "workflows=pr-test-amd.yml" >> "$GITHUB_OUTPUT"
+          else
+            echo "workflows=pr-test-amd.yml,nightly-test-amd.yml,pr-test-amd-rocm720.yml,nightly-test-amd-rocm720.yml" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Fetch Actions data snapshot
+        timeout-minutes: 30
+        run: |
+          python scripts/ci/utils/query_job_status.py \
+            --repo ${{ github.repository }} \
+            --workflow "${{ steps.select-workflows.outputs.workflows }}" \
+            --hours ${{ inputs.hours || '24' }} \
+            --dump-data-file actions-job-snapshot.json
+
+      - name: Upload Actions data snapshot
+        uses: actions/upload-artifact@v4
+        with:
+          name: actions-job-snapshot
+          path: actions-job-snapshot.json
+          if-no-files-found: error
+
+  # Single job filter mode
+  custom-report:
+    name: Custom Job Report
+    if: ${{ inputs.job_filter }}
+    needs: fetch-actions-data
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: pip install tabulate
+
+      - name: Download Actions data snapshot
+        uses: actions/download-artifact@v4
+        with:
+          name: actions-job-snapshot
+          path: ci-data
+
+      - name: Generate Custom Job Report
+        timeout-minutes: 30
+        run: |
+          python scripts/ci/utils/query_job_status.py \
+            --repo ${{ github.repository }} \
+            --job "${{ inputs.job_filter }}" \
+            --workflow "pr-test-amd.yml" \
+            --hours ${{ inputs.hours || '24' }} \
+            --input-data-file ci-data/actions-job-snapshot.json \
+            --summary
+
+  # Parse workflow files to get job names dynamically
+  parse-workflows:
+    name: Parse Workflow Jobs
+    if: ${{ !inputs.job_filter }}
+    runs-on: ubuntu-latest
+    outputs:
+      pr_jobs: ${{ steps.parse.outputs.pr_jobs }}
+      nightly_jobs: ${{ steps.parse.outputs.nightly_jobs }}
+      pr_rocm720_jobs: ${{ steps.parse.outputs.pr_rocm720_jobs }}
+      nightly_rocm720_jobs: ${{ steps.parse.outputs.nightly_rocm720_jobs }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Parse workflow files
+        id: parse
+        run: |
+          # Parse pr-test-amd.yml and extract job names (exclude utility jobs)
+          # Excluded: call-gate, check-changes, pr-test-amd-finish, cancel, check-all-jobs
+          pr_jobs=$(yq -r '.jobs | keys | .[]' .github/workflows/pr-test-amd.yml | \
+            grep -v -E '^(call-gate|check-changes|pr-test-amd-finish|cancel|check-all-jobs)$' | \
+            jq -R -s -c 'split("\n") | map(select(length > 0))')
+          echo "pr_jobs=$pr_jobs" >> $GITHUB_OUTPUT
+          echo "PR jobs: $pr_jobs"
+
+          # Parse nightly-test-amd.yml and extract job names (exclude utility jobs)
+          # Excluded: check-all-jobs
+          nightly_jobs=$(yq -r '.jobs | keys | .[]' .github/workflows/nightly-test-amd.yml | \
+            grep -v -E '^(check-all-jobs)$' | \
+            jq -R -s -c 'split("\n") | map(select(length > 0))')
+          echo "nightly_jobs=$nightly_jobs" >> $GITHUB_OUTPUT
+          echo "Nightly jobs: $nightly_jobs"
+
+          # Parse pr-test-amd-rocm720.yml (exclude utility jobs)
+          # Excluded: call-gate, check-changes, pr-test-amd-finish, cancel, check-all-jobs
+          pr_rocm720_jobs=$(yq -r '.jobs | keys | .[]' .github/workflows/pr-test-amd-rocm720.yml | \
+            grep -v -E '^(call-gate|check-changes|pr-test-amd-finish|cancel|check-all-jobs)$' | \
+            jq -R -s -c 'split("\n") | map(select(length > 0))')
+          echo "pr_rocm720_jobs=$pr_rocm720_jobs" >> $GITHUB_OUTPUT
+          echo "PR ROCm 7.2 jobs: $pr_rocm720_jobs"
+
+          # Parse nightly-test-amd-rocm720.yml (exclude utility jobs)
+          # Excluded: check-all-jobs
+          nightly_rocm720_jobs=$(yq -r '.jobs | keys | .[]' .github/workflows/nightly-test-amd-rocm720.yml | \
+            grep -v -E '^(check-all-jobs)$' | \
+            jq -R -s -c 'split("\n") | map(select(length > 0))')
+          echo "nightly_rocm720_jobs=$nightly_rocm720_jobs" >> $GITHUB_OUTPUT
+          echo "Nightly ROCm 7.2 jobs: $nightly_rocm720_jobs"
+
+  # PR CI reports using dynamic matrix
+  pr-ci-reports:
+    name: PR - ${{ matrix.job_name }}
+    needs: [parse-workflows, fetch-actions-data]
+    if: ${{ !inputs.job_filter }}
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        job_name: ${{ fromJson(needs.parse-workflows.outputs.pr_jobs) }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: pip install tabulate
+
+      - name: Download Actions data snapshot
+        uses: actions/download-artifact@v4
+        with:
+          name: actions-job-snapshot
+          path: ci-data
+
+      - name: Generate Report
+        timeout-minutes: 15
+        run: |
+          python scripts/ci/utils/query_job_status.py \
+            --repo ${{ github.repository }} \
+            --job "${{ matrix.job_name }}" \
+            --workflow "pr-test-amd.yml" \
+            --hours ${{ inputs.hours || '24' }} \
+            --input-data-file ci-data/actions-job-snapshot.json \
+            --summary
+
+  # Nightly AMD test reports using dynamic matrix
+  nightly-reports:
+    name: Nightly - ${{ matrix.job_name }}
+    needs: [parse-workflows, fetch-actions-data]
+    if: ${{ !inputs.job_filter }}
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        job_name: ${{ fromJson(needs.parse-workflows.outputs.nightly_jobs) }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: pip install tabulate
+
+      - name: Download Actions data snapshot
+        uses: actions/download-artifact@v4
+        with:
+          name: actions-job-snapshot
+          path: ci-data
+
+      - name: Generate Nightly Report
+        timeout-minutes: 15
+        run: |
+          python scripts/ci/utils/query_job_status.py \
+            --repo ${{ github.repository }} \
+            --job "${{ matrix.job_name }}" \
+            --workflow "nightly-test-amd.yml" \
+            --hours ${{ inputs.hours || '24' }} \
+            --input-data-file ci-data/actions-job-snapshot.json \
+            --summary
+
+  # PR ROCm 7.2 CI reports using dynamic matrix
+  pr-rocm720-ci-reports:
+    name: PR ROCm720 - ${{ matrix.job_name }}
+    needs: [parse-workflows, fetch-actions-data]
+    if: ${{ !inputs.job_filter }}
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        job_name: ${{ fromJson(needs.parse-workflows.outputs.pr_rocm720_jobs) }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: pip install tabulate
+
+      - name: Download Actions data snapshot
+        uses: actions/download-artifact@v4
+        with:
+          name: actions-job-snapshot
+          path: ci-data
+
+      - name: Generate PR ROCm 7.2 Report
+        timeout-minutes: 15
+        run: |
+          python scripts/ci/utils/query_job_status.py \
+            --repo ${{ github.repository }} \
+            --job "${{ matrix.job_name }}" \
+            --workflow "pr-test-amd-rocm720.yml" \
+            --hours ${{ inputs.hours || '24' }} \
+            --input-data-file ci-data/actions-job-snapshot.json \
+            --summary
+
+  # Nightly ROCm 7.2 reports using dynamic matrix
+  nightly-rocm720-reports:
+    name: Nightly ROCm720 - ${{ matrix.job_name }}
+    needs: [parse-workflows, fetch-actions-data]
+    if: ${{ !inputs.job_filter }}
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        job_name: ${{ fromJson(needs.parse-workflows.outputs.nightly_rocm720_jobs) }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: pip install tabulate
+
+      - name: Download Actions data snapshot
+        uses: actions/download-artifact@v4
+        with:
+          name: actions-job-snapshot
+          path: ci-data
+
+      - name: Generate Nightly ROCm 7.2 Report
+        timeout-minutes: 15
+        run: |
+          python scripts/ci/utils/query_job_status.py \
+            --repo ${{ github.repository }} \
+            --job "${{ matrix.job_name }}" \
+            --workflow "nightly-test-amd-rocm720.yml" \
+            --hours ${{ inputs.hours || '24' }} \
+            --input-data-file ci-data/actions-job-snapshot.json \
+            --summary
+
+  # Runner fleet report - cross-workflow runner analytics in a single pass
+  runner-fleet-report:
+    name: Runner Fleet Report
+    if: ${{ !inputs.job_filter }}
+    needs: fetch-actions-data
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: pip install tabulate
+
+      - name: Download Actions data snapshot
+        uses: actions/download-artifact@v4
+        with:
+          name: actions-job-snapshot
+          path: ci-data
+
+      - name: Generate Runner Fleet Report
+        timeout-minutes: 30
+        run: |
+          python scripts/ci/utils/query_job_status.py \
+            --repo ${{ github.repository }} \
+            --runner-report \
+            --workflow "pr-test-amd.yml,nightly-test-amd.yml,pr-test-amd-rocm720.yml,nightly-test-amd-rocm720.yml" \
+            --hours ${{ inputs.hours || '24' }} \
+            --input-data-file ci-data/actions-job-snapshot.json \
+            --summary

third_party/sglang/.github/workflows/auto-tune.yml

@@ -0,0 +1,10 @@
+name: Auto tune
+
+on:
+  workflow_dispatch:
+
+jobs:
+  auto-tune-lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4

third_party/sglang/.github/workflows/bot-bump-flashinfer-version.yml

@@ -0,0 +1,50 @@
+name: Bot Bump Flashinfer Version
+
+on:
+  workflow_dispatch:
+    inputs:
+      new_version:
+        description: 'New flashinfer version (e.g., 0.6.4)'
+        required: true
+        type: string
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  bump-flashinfer-version:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install Python dependencies
+        run: |
+            pip install tomli
+
+      - name: Configure Git and branch
+        run: |
+          git config user.name "sglang-bot"
+          git config user.email "sglang-bot@users.noreply.github.com"
+          RANDOM_SUFFIX=$(echo $RANDOM | md5sum | head -c 4)
+          BRANCH_NAME="bot/bump-flashinfer-version-${{ github.event.inputs.new_version }}-${RANDOM_SUFFIX}"
+          git checkout -b "$BRANCH_NAME"
+          echo "BRANCH_NAME=$BRANCH_NAME" >> $GITHUB_ENV
+
+      - name: Run flashinfer version bump script
+        run: |
+          python scripts/release/bump_flashinfer_version.py "${{ github.event.inputs.new_version }}"
+
+      - name: Commit and create PR
+        env:
+          GH_TOKEN: ${{ secrets.GH_PAT_FOR_PULL_REQUEST }}
+        run: |
+          bash scripts/release/commit_and_pr.sh "flashinfer" "${{ github.event.inputs.new_version }}" "$BRANCH_NAME"

third_party/sglang/.github/workflows/bot-bump-kernel-version-to-sglang.yml

@@ -0,0 +1,60 @@
+name: Bot Bump Kernel Version to SGLang
+
+on:
+  workflow_dispatch:
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  bump-kernel-version-to-sglang:
+    runs-on: ubuntu-latest
+    outputs:
+      branch_name: ${{ steps.set_output.outputs.branch_name }}
+      needs_sync: ${{ steps.check_sync.outputs.needs_sync }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install Python dependencies
+        run: |
+          pip install tomli
+
+      - name: Check if sync is needed
+        id: check_sync
+        run: |
+          python scripts/release/check_kernel_version_to_sglang.py
+
+      - name: Configure Git and branch
+        if: steps.check_sync.outputs.needs_sync == 'true'
+        id: set_output
+        run: |
+          git config user.name "sglang-bot"
+          git config user.email "sglang-bot@users.noreply.github.com"
+          RANDOM_SUFFIX=$(echo $RANDOM | md5sum | head -c 4)
+          KERNEL_VERSION="${{ steps.check_sync.outputs.kernel_version }}"
+          BRANCH_NAME="bot/bump-kernel-version-to-sglang-${KERNEL_VERSION}-${RANDOM_SUFFIX}"
+          git checkout -b "$BRANCH_NAME"
+          echo "BRANCH_NAME=$BRANCH_NAME" >> $GITHUB_ENV
+          echo "KERNEL_VERSION=$KERNEL_VERSION" >> $GITHUB_ENV
+          echo "branch_name=$BRANCH_NAME" >> $GITHUB_OUTPUT
+
+      - name: Run kernel version bump script
+        if: steps.check_sync.outputs.needs_sync == 'true'
+        run: |
+          python scripts/release/bump_kernel_version_to_sglang.py
+
+      - name: Commit and create PR
+        if: steps.check_sync.outputs.needs_sync == 'true'
+        env:
+          GH_TOKEN: ${{ secrets.GH_PAT_FOR_PULL_REQUEST }}
+        run: |
+          bash scripts/release/commit_and_pr_kernel_to_sglang.sh "$KERNEL_VERSION" "$BRANCH_NAME"

third_party/sglang/.github/workflows/bot-bump-kernel-version.yml

@@ -0,0 +1,50 @@
+name: Bot Bump Kernel Version
+
+on:
+  workflow_dispatch:
+    inputs:
+      new_version:
+        description: 'New sgl-kernel version (e.g., 0.3.12)'
+        required: true
+        type: string
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  bump-kernel-version:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install Python dependencies
+        run: |
+          pip install tomli
+
+      - name: Configure Git and branch
+        run: |
+          git config user.name "sglang-bot"
+          git config user.email "sglang-bot@users.noreply.github.com"
+          RANDOM_SUFFIX=$(echo $RANDOM | md5sum | head -c 4)
+          BRANCH_NAME="bot/bump-kernel-version-${{ github.event.inputs.new_version }}-${RANDOM_SUFFIX}"
+          git checkout -b "$BRANCH_NAME"
+          echo "BRANCH_NAME=$BRANCH_NAME" >> $GITHUB_ENV
+
+      - name: Run kernel version bump script
+        run: |
+          python scripts/release/bump_kernel_version.py "${{ github.event.inputs.new_version }}"
+
+      - name: Commit and create PR
+        env:
+          GH_TOKEN: ${{ secrets.GH_PAT_FOR_PULL_REQUEST }}
+        run: |
+          bash scripts/release/commit_and_pr.sh "sgl-kernel" "${{ github.event.inputs.new_version }}" "$BRANCH_NAME"

third_party/sglang/.github/workflows/bot-bump-sglang-version.yml

@@ -0,0 +1,89 @@
+name: Bot Bump SGLang Version
+
+on:
+  workflow_dispatch:
+    inputs:
+      new_version:
+        description: 'New SGLang version (e.g., 0.5.3 or 0.5.3rc0)'
+        required: true
+        type: string
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  bump-sglang-version:
+    runs-on: ubuntu-latest
+    outputs:
+      branch_name: ${{ steps.set_output.outputs.branch_name }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install Python dependencies
+        run: |
+          pip install tomli
+
+      - name: Configure Git and branch
+        id: set_output
+        run: |
+          git config user.name "sglang-bot"
+          git config user.email "sglang-bot@users.noreply.github.com"
+          RANDOM_SUFFIX=$(echo $RANDOM | md5sum | head -c 4)
+          BRANCH_NAME="bot/bump-sglang-version-${{ github.event.inputs.new_version }}-${RANDOM_SUFFIX}"
+          git checkout -b "$BRANCH_NAME"
+          echo "BRANCH_NAME=$BRANCH_NAME" >> $GITHUB_ENV
+          echo "branch_name=$BRANCH_NAME" >> $GITHUB_OUTPUT
+
+      - name: Run SGLang version bump script
+        run: |
+          python scripts/release/bump_sglang_version.py "${{ github.event.inputs.new_version }}"
+
+      - name: Commit and create PR
+        env:
+          GH_TOKEN: ${{ secrets.GH_PAT_FOR_PULL_REQUEST }}
+        run: |
+          bash scripts/release/commit_and_pr.sh "SGLang" "${{ github.event.inputs.new_version }}" "$BRANCH_NAME"
+
+  run-nightly-tests-nvidia:
+    needs: bump-sglang-version
+    uses: ./.github/workflows/nightly-test-nvidia.yml
+    with:
+      ref: ${{ needs.bump-sglang-version.outputs.branch_name }}
+    secrets: inherit
+
+  run-nightly-tests-amd:
+    needs: bump-sglang-version
+    uses: ./.github/workflows/nightly-test-amd.yml
+    with:
+      ref: ${{ needs.bump-sglang-version.outputs.branch_name }}
+    secrets: inherit
+
+  run-nightly-tests-npu:
+    needs: bump-sglang-version
+    uses: ./.github/workflows/nightly-test-npu.yml
+    with:
+      ref: ${{ needs.bump-sglang-version.outputs.branch_name }}
+    secrets: inherit
+
+  run-pr-tests-xeon:
+    needs: bump-sglang-version
+    uses: ./.github/workflows/pr-test-xeon.yml
+    with:
+      ref: ${{ needs.bump-sglang-version.outputs.branch_name }}
+    secrets: inherit
+
+  run-pr-tests-xpu:
+    needs: bump-sglang-version
+    uses: ./.github/workflows/pr-test-xpu.yml
+    with:
+      ref: ${{ needs.bump-sglang-version.outputs.branch_name }}
+    secrets: inherit

third_party/sglang/.github/workflows/bot-cherry-pick.yml

@@ -0,0 +1,182 @@
+name: Bot Cherry Pick to Release Branch
+
+on:
+  workflow_dispatch:
+    inputs:
+      commit_sha:
+        description: 'Commit SHA to cherry-pick (full or short hash)'
+        required: true
+        type: string
+      target_branch:
+        description: 'Target release branch (e.g., release/v0.5.7)'
+        required: true
+        type: string
+      create_pr:
+        description: 'Create a PR instead of pushing directly'
+        required: false
+        type: boolean
+        default: true
+
+permissions:
+  contents: write
+  pull-requests: write
+
+concurrency:
+  group: cherry-pick-${{ github.event.inputs.target_branch }}
+  cancel-in-progress: false
+
+jobs:
+  cherry-pick:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: ubuntu-latest
+    environment: 'prod'
+    steps:
+      - name: Validate inputs
+        env:
+          TARGET_BRANCH: ${{ github.event.inputs.target_branch }}
+        run: |
+          if [[ ! "$TARGET_BRANCH" =~ ^release/v[0-9]+\.[0-9]+(\.[0-9]+)?$ ]]; then
+            echo "::error::Target branch must match pattern 'release/vX.Y' or 'release/vX.Y.Z' (e.g., release/v0.5.7)"
+            exit 1
+          fi
+
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          token: ${{ secrets.GH_PAT_FOR_PULL_REQUEST }}
+
+      - name: Configure Git
+        run: |
+          git config user.name "sglang-bot"
+          git config user.email "sglang-bot@users.noreply.github.com"
+
+      - name: Validate target branch exists
+        env:
+          TARGET_BRANCH: ${{ github.event.inputs.target_branch }}
+        run: |
+          git fetch origin
+          if ! git ls-remote --exit-code --heads origin "$TARGET_BRANCH" > /dev/null 2>&1; then
+            echo "::error::Target branch '$TARGET_BRANCH' does not exist on remote"
+            exit 1
+          fi
+
+      - name: Get commit info
+        id: commit_info
+        env:
+          COMMIT_SHA_INPUT: ${{ github.event.inputs.commit_sha }}
+        run: |
+          # Verify commit exists
+          if ! git cat-file -t "$COMMIT_SHA_INPUT" > /dev/null 2>&1; then
+            echo "::error::Commit SHA '$COMMIT_SHA_INPUT' does not exist"
+            exit 1
+          fi
+
+          # Get full SHA if short hash provided
+          FULL_SHA=$(git rev-parse "$COMMIT_SHA_INPUT")
+          COMMIT_TITLE=$(git log -1 --format="%s" "$FULL_SHA")
+          SHORT_SHA=$(git rev-parse --short "$FULL_SHA")
+          echo "full_sha=$FULL_SHA" >> $GITHUB_OUTPUT
+          echo "short_sha=$SHORT_SHA" >> $GITHUB_OUTPUT
+          # Use delimiter for multiline-safe output
+          {
+            echo "commit_title<<EOF"
+            echo "$COMMIT_TITLE"
+            echo "EOF"
+          } >> $GITHUB_OUTPUT
+          echo "Cherry-picking commit: $SHORT_SHA - $COMMIT_TITLE"
+
+      - name: Cherry-pick commit
+        id: cherry_pick
+        env:
+          TARGET_BRANCH: ${{ github.event.inputs.target_branch }}
+          FULL_SHA: ${{ steps.commit_info.outputs.full_sha }}
+          SHORT_SHA: ${{ steps.commit_info.outputs.short_sha }}
+          CREATE_PR: ${{ github.event.inputs.create_pr }}
+        run: |
+          if [[ "$CREATE_PR" == "true" ]]; then
+            # Create a new branch for the PR
+            RANDOM_SUFFIX=$(head -c 4 /dev/urandom | xxd -p)
+            NEW_BRANCH="cherry-pick/${SHORT_SHA}-to-${TARGET_BRANCH#release/}-${RANDOM_SUFFIX}"
+            git checkout -b "$NEW_BRANCH" "origin/$TARGET_BRANCH"
+            echo "new_branch=$NEW_BRANCH" >> $GITHUB_OUTPUT
+          else
+            # Checkout target branch directly
+            git checkout "$TARGET_BRANCH"
+          fi
+
+          # Attempt cherry-pick
+          if git cherry-pick "$FULL_SHA"; then
+            echo "cherry_pick_success=true" >> $GITHUB_OUTPUT
+          else
+            echo "::error::Cherry-pick failed due to conflicts. Please resolve manually."
+            git cherry-pick --abort || true
+            echo "cherry_pick_success=false" >> $GITHUB_OUTPUT
+            exit 1
+          fi
+
+      - name: Push changes
+        if: steps.cherry_pick.outputs.cherry_pick_success == 'true'
+        env:
+          CREATE_PR: ${{ github.event.inputs.create_pr }}
+          TARGET_BRANCH: ${{ github.event.inputs.target_branch }}
+          NEW_BRANCH: ${{ steps.cherry_pick.outputs.new_branch }}
+        run: |
+          if [[ "$CREATE_PR" == "true" ]]; then
+            git push origin "$NEW_BRANCH"
+          else
+            git push origin "$TARGET_BRANCH"
+          fi
+
+      - name: Create Pull Request
+        if: steps.cherry_pick.outputs.cherry_pick_success == 'true' && github.event.inputs.create_pr == 'true'
+        env:
+          GH_TOKEN: ${{ secrets.GH_PAT_FOR_PULL_REQUEST }}
+          TARGET_BRANCH: ${{ github.event.inputs.target_branch }}
+          SHORT_SHA: ${{ steps.commit_info.outputs.short_sha }}
+          COMMIT_TITLE: ${{ steps.commit_info.outputs.commit_title }}
+          FULL_SHA: ${{ steps.commit_info.outputs.full_sha }}
+          NEW_BRANCH: ${{ steps.cherry_pick.outputs.new_branch }}
+        run: |
+          PR_TITLE="[Cherry-pick] ${COMMIT_TITLE} to ${TARGET_BRANCH}"
+
+          gh pr create \
+            --title "$PR_TITLE" \
+            --base "$TARGET_BRANCH" \
+            --head "$NEW_BRANCH" \
+            --label "cherry-pick" \
+            --body-file - <<EOF
+          Cherry-pick of commit ${FULL_SHA} to \`${TARGET_BRANCH}\`
+
+          **Original commit:** ${FULL_SHA}
+          **Original title:** ${COMMIT_TITLE}
+
+          ---
+          *This PR was automatically created by the cherry-pick workflow.*
+          EOF
+
+      - name: Summary
+        if: always()
+        env:
+          FULL_SHA: ${{ steps.commit_info.outputs.full_sha }}
+          COMMIT_TITLE: ${{ steps.commit_info.outputs.commit_title }}
+          TARGET_BRANCH: ${{ github.event.inputs.target_branch }}
+          CHERRY_PICK_SUCCESS: ${{ steps.cherry_pick.outputs.cherry_pick_success }}
+          CREATE_PR: ${{ github.event.inputs.create_pr }}
+          NEW_BRANCH: ${{ steps.cherry_pick.outputs.new_branch }}
+          ACTOR: ${{ github.actor }}
+        run: |
+          echo "## Cherry-Pick Summary" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "- **Triggered by:** @${ACTOR}" >> $GITHUB_STEP_SUMMARY
+          echo "- **Commit:** ${FULL_SHA}" >> $GITHUB_STEP_SUMMARY
+          echo "- **Title:** ${COMMIT_TITLE}" >> $GITHUB_STEP_SUMMARY
+          echo "- **Target Branch:** ${TARGET_BRANCH}" >> $GITHUB_STEP_SUMMARY
+          if [[ "$CHERRY_PICK_SUCCESS" == "true" ]]; then
+            echo "- **Status:** ✅ Success" >> $GITHUB_STEP_SUMMARY
+          else
+            echo "- **Status:** ❌ Failed" >> $GITHUB_STEP_SUMMARY
+          fi
+          if [[ "$CREATE_PR" == "true" && "$CHERRY_PICK_SUCCESS" == "true" ]]; then
+            echo "- **PR Branch:** ${NEW_BRANCH}" >> $GITHUB_STEP_SUMMARY
+          fi

third_party/sglang/.github/workflows/cancel-pr-workflow-on-merge.yml

@@ -0,0 +1,22 @@
+name: Cancel PR Workflows on Merge
+
+on:
+  pull_request_target:
+    types:
+      - closed
+
+permissions:
+  actions: write
+
+jobs:
+  cancel:
+    if: github.event.pull_request.merged == true
+    runs-on: ubuntu-latest
+    steps:
+      - name: Cancel Previous Runs
+        uses: styfle/cancel-workflow-action@0.12.1
+        with:
+          workflow_id: all
+          access_token: ${{ secrets.GITHUB_TOKEN }}
+          ignore_sha: true
+          pr_number: ${{ github.event.pull_request.number }}

third_party/sglang/.github/workflows/cancel-unfinished-pr-tests.yml

@@ -0,0 +1,155 @@
+name: Cancel Unfinished PR Runs
+
+on:
+  workflow_dispatch:
+    inputs:
+      workflows:
+        description: 'Space-separated list of workflow filenames to cancel'
+        required: true
+        type: string
+        default: 'pr-test.yml'
+      include_high_priority:
+        description: 'Also cancel runs from high-priority PRs'
+        required: false
+        type: boolean
+        default: false
+
+permissions:
+  actions: write   # Needed to cancel runs
+  contents: read   # Needed to read repo info
+  pull-requests: read  # needed for gh pr view (labels)
+
+jobs:
+  cancel-unfinished-pr-runs:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Install GitHub CLI
+        run: sudo apt-get install -y gh jq
+
+      - name: Cancel unfinished PR-associated runs (skip high-priority PRs)
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          REPO: ${{ github.repository }}
+          WORKFLOWS: ${{ github.event.inputs.workflows || 'pr-test.yml' }}
+          INCLUDE_HIGH_PRIORITY: ${{ github.event.inputs.include_high_priority || 'false' }}
+        shell: bash
+        run: |
+          set -euo pipefail
+
+          # Read the space-separated string from the input into a bash array
+          read -r -a WORKFLOW_FILES <<< "${WORKFLOWS}"
+
+          echo "Targeting ${#WORKFLOW_FILES[@]} workflow(s): ${WORKFLOWS}"
+          echo ""
+
+          for workflow_file in "${WORKFLOW_FILES[@]}"; do
+            echo "========================================="
+            echo "Workflow: $workflow_file"
+            echo "========================================="
+
+            # Get all unfinished runs
+            all_runs=$(gh run list \
+              --repo "$REPO" \
+              --workflow "$workflow_file" \
+              --json databaseId,status,event,url,createdAt \
+              --limit 1000 \
+            | jq -c '.[] | select(.status=="queued" or .status=="waiting" or .status=="in_progress")')
+
+            if [ -z "$all_runs" ]; then
+              echo "✅ No unfinished runs found"
+              echo ""
+              continue
+            fi
+
+            # Count runs by event type
+            total_runs=$(echo "$all_runs" | wc -l)
+            pr_runs=$(echo "$all_runs" | jq -s '[.[] | select(.event=="pull_request")] | length')
+            other_runs=$(echo "$all_runs" | jq -s '[.[] | select(.event!="pull_request")] | length')
+
+            echo "📊 Summary: $total_runs unfinished runs ($pr_runs PR-related, $other_runs other)"
+            echo ""
+
+            # Process non-PR runs first
+            if [ "$other_runs" -gt 0 ]; then
+              echo "--- Non-PR Runs ---"
+              echo "$all_runs" | jq -c 'select(.event!="pull_request")' | while read -r run; do
+                run_url=$(echo "$run" | jq -r '.url')
+                run_event=$(echo "$run" | jq -r '.event')
+                run_status=$(echo "$run" | jq -r '.status')
+                echo "  • $run_event ($run_status): $run_url"
+              done
+              echo ""
+            fi
+
+            # Process PR runs
+            if [ "$pr_runs" -gt 0 ]; then
+              echo "--- PR Runs (checking for cancellation) ---"
+              echo "$all_runs" | jq -c 'select(.event=="pull_request")' | while read -r run; do
+                run_id=$(echo "$run" | jq -r '.databaseId')
+                run_url=$(echo "$run" | jq -r '.url')
+                run_status=$(echo "$run" | jq -r '.status')
+
+                echo ""
+                echo "Run ($run_status): $run_url"
+
+                # Fetch full run details to get head repository and branch info
+                run_details=$(gh api -H "Accept: application/vnd.github+json" \
+                  "repos/$REPO/actions/runs/$run_id" 2>/dev/null || true)
+
+                if [ -z "$run_details" ]; then
+                  echo "  ⚠️  Could not fetch run details, skipping"
+                  continue
+                fi
+
+                # Get head owner and branch (works for both fork and non-fork PRs)
+                head_owner=$(echo "$run_details" | jq -r '.head_repository.owner.login // empty')
+                head_branch=$(echo "$run_details" | jq -r '.head_branch // empty')
+
+                if [ -z "$head_owner" ] || [ -z "$head_branch" ]; then
+                  echo "  ⚠️  Missing head info, skipping"
+                  continue
+                fi
+
+                echo "  Branch: ${head_owner}:${head_branch}"
+
+                # Find PR by searching with head=owner:branch
+                pr_number=$(gh api -H "Accept: application/vnd.github+json" \
+                  "repos/$REPO/pulls?state=open&head=${head_owner}:${head_branch}" \
+                  --jq '.[0].number // empty' 2>/dev/null || true)
+
+                if [ -z "$pr_number" ]; then
+                  echo "  ⚠️  No open PR found, skipping"
+                  continue
+                fi
+
+                pr_url="https://github.com/$REPO/pull/$pr_number"
+                echo "  PR: $pr_url"
+
+                # Check for high priority label
+                labels=$(gh pr view "$pr_number" --repo "$REPO" --json labels \
+                  | jq -r '.labels[].name' 2>/dev/null || true)
+
+                if echo "$labels" | grep -Fxq "bypass-maintenance"; then
+                  echo "  🛑 Skipping (bypass-maintenance label, never cancelled)"
+                  continue
+                fi
+
+                if echo "$labels" | grep -Fxq "high priority"; then
+                  if [ "$INCLUDE_HIGH_PRIORITY" != "true" ]; then
+                    echo "  🛑 Skipping (high priority label)"
+                    continue
+                  fi
+                  echo "  ⚠️  High priority PR, but include_high_priority is enabled"
+                fi
+
+                echo "  🚫 Cancelling..."
+                gh run cancel "$run_id" --repo "$REPO" || echo "  ⚠️  Cancellation failed"
+              done
+            fi
+
+            echo ""
+          done
+
+          echo "========================================="
+          echo "✅ Processing complete"
+          echo "========================================="

third_party/sglang/.github/workflows/ci-coverage-overview.yml

@@ -0,0 +1,154 @@
+name: CI Coverage Overview
+
+on:
+  schedule:
+    - cron: '0 6 * * *'  # Daily at 6 AM UTC
+  pull_request:
+    paths:
+      - '.github/workflows/ci-coverage-overview.yml'
+      - 'scripts/ci/utils/ci_coverage_report.py'
+      - 'test/registered/**'
+  workflow_dispatch:
+    inputs:
+      output_format:
+        description: 'Output format'
+        required: false
+        default: 'markdown'
+        type: choice
+        options:
+          - markdown
+          - json
+
+jobs:
+  summary:
+    name: Summary
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Generate Summary Report
+        run: |
+          python scripts/ci/utils/ci_coverage_report.py --section summary
+
+  by-folder:
+    name: Tests by Folder
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Generate Tests by Folder Report
+        run: |
+          python scripts/ci/utils/ci_coverage_report.py --section by-folder
+
+  by-suite:
+    name: Tests by Suite
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Generate Tests by Suite Report
+        run: |
+          python scripts/ci/utils/ci_coverage_report.py --section by-suite
+
+  unit-test-coverage:
+    name: Unit Test Code Coverage
+    if: github.event_name != 'pull_request'
+    runs-on: 1-gpu-h100
+    timeout-minutes: 30
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install dependencies
+        timeout-minutes: 10
+        run: |
+          pip install -e "python/[test]"
+
+      - name: Run unit tests with coverage
+        timeout-minutes: 10
+        run: |
+          pytest test/registered/unit/ \
+            --cov --cov-config=.coveragerc \
+            --cov-report=term-missing:skip-covered \
+            --continue-on-collection-errors \
+            -v | tee coverage_output.txt
+
+      - name: Write coverage to summary
+        if: always()
+        run: |
+          echo "## Unit Test Code Coverage" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "**Commit:** \`${GITHUB_SHA::8}\` | **Branch:** \`${GITHUB_REF_NAME}\`" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+
+          # Test result line (e.g., "== 42 passed, 1 failed in 23.5s ==")
+          echo '```' >> $GITHUB_STEP_SUMMARY
+          grep -E '^=+.*passed' coverage_output.txt >> $GITHUB_STEP_SUMMARY || true
+          echo "" >> $GITHUB_STEP_SUMMARY
+          # Coverage total
+          grep -E '^TOTAL ' coverage_output.txt >> $GITHUB_STEP_SUMMARY || true
+          echo '```' >> $GITHUB_STEP_SUMMARY
+
+          # Partially covered core modules (1-49%) — most actionable for contributors
+          # Only show modules with testable logic; skip configs, models, layers, etc.
+          LOW_COV=$(awk '/^python\/.*%/ {
+            for (i=1; i<=NF; i++) {
+              if ($i ~ /^[0-9]+%$/) {
+                pct = $i + 0
+                if (pct >= 1 && pct < 50) printf "%-80s %5s  %s\n", $1, $(i-2), $i
+                break
+              }
+            }
+          }' coverage_output.txt \
+            | grep -E '/(mem_cache|managers|sampling|parser|observability|function_call|entrypoints|speculative|multimodal|utils)/' \
+            | head -40 || true)
+          if [ -n "$LOW_COV" ]; then
+            echo "" >> $GITHUB_STEP_SUMMARY
+            echo "<details><summary>Core modules with coverage below 50% — good candidates for more unit tests</summary>" >> $GITHUB_STEP_SUMMARY
+            echo "" >> $GITHUB_STEP_SUMMARY
+            echo '```' >> $GITHUB_STEP_SUMMARY
+            echo "$LOW_COV" >> $GITHUB_STEP_SUMMARY
+            echo '```' >> $GITHUB_STEP_SUMMARY
+            echo "</details>" >> $GITHUB_STEP_SUMMARY
+          fi
+
+  json-export:
+    name: JSON Export
+    runs-on: ubuntu-latest
+    if: inputs.output_format == 'json'
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Generate JSON Report
+        run: |
+          python scripts/ci/utils/ci_coverage_report.py --output-format json > ci_coverage.json
+
+      - name: Upload JSON artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: ci-coverage-report
+          path: ci_coverage.json

third_party/sglang/.github/workflows/ci-failure-monitor.yml

@@ -0,0 +1,72 @@
+name: CI Failure Monitor
+
+on:
+  schedule:
+    - cron: '0 */12 * * *' # Every 12 hour
+  workflow_dispatch:
+
+concurrency:
+  group: ci-failure-monitor-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+  actions: read
+
+jobs:
+  failure-analysis:
+    if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.14'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install requests slack_sdk
+
+      - name: Run Failure Analysis
+        env:
+          GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
+          GH_PAT_FOR_RUNNER_ADMIN: ${{ secrets.GH_PAT_FOR_RUNNER_ADMIN }}
+          PYTHONUNBUFFERED: 1
+          PYTHONIOENCODING: utf-8
+        run: |
+          cd scripts/ci_monitor
+          python ci_failures_analysis.py \
+            --token $GITHUB_TOKEN \
+            --limit 100 \
+            --output ci_failure_analysis_$(date +%Y%m%d_%H%M%S).json
+
+      - name: Upload Analysis Results
+        uses: actions/upload-artifact@v4
+        with:
+          name: ci-failure-analysis-${{ github.run_number }}
+          path: |
+            scripts/ci_monitor/ci_failure_analysis_*.json
+          retention-days: 7
+
+      - name: Send Slack Notification
+        if: always()
+        env:
+          SGLANG_DIFFUSION_SLACK_TOKEN: ${{ secrets.SGLANG_DIFFUSION_SLACK_TOKEN }}
+        run: |
+          cd scripts/ci_monitor
+          LATEST_REPORT=$(ls -t ci_failure_analysis_*.json | head -1)
+
+          if [ ! -f "$LATEST_REPORT" ]; then
+            echo "No report found, so skipping Slack notification"
+            exit 0
+          fi
+
+          if [ -n "$SGLANG_DIFFUSION_SLACK_TOKEN" ]; then
+            python3 post_ci_failures_to_slack.py --report-file "$LATEST_REPORT"
+          else
+            echo "SGLANG_DIFFUSION_SLACK_TOKEN not configured, skipping notification"
+          fi

third_party/sglang/.github/workflows/close-inactive-issues.yml

@@ -0,0 +1,96 @@
+name: Close Inactive Issues
+
+on:
+  schedule:
+    - cron: '0 0 * * *'
+  workflow_dispatch:
+
+permissions:
+  issues: write
+  contents: read
+
+jobs:
+  close-inactive-issues:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check and close inactive issues
+        uses: actions/github-script@v6
+        with:
+          github-token: ${{secrets.GITHUB_TOKEN}}
+          script: |
+            const sixtyDaysAgo = new Date(Date.now() - 60 * 24 * 60 * 60 * 1000);
+
+            const [owner, repo] = process.env.GITHUB_REPOSITORY.split('/');
+            console.log(`Owner: ${owner}, Repo: ${repo}`);
+
+            async function fetchIssues(page = 1) {
+              console.log(`Fetching issues for ${owner}/${repo}, page ${page}`);
+              return await github.rest.issues.listForRepo({
+                owner,
+                repo,
+                state: 'open',
+                sort: 'updated',
+                direction: 'asc',
+                per_page: 100,
+                page: page
+              });
+            }
+
+            async function processIssues() {
+              console.log('Starting to process issues');
+              console.log(`Repository: ${owner}/${repo}`);
+
+              let page = 1;
+              let hasMoreIssues = true;
+              while (hasMoreIssues) {
+                try {
+                  const issues = await fetchIssues(page);
+                  console.log(`Fetched ${issues.data.length} issues on page ${page}`);
+
+                  if (issues.data.length === 0) {
+                    hasMoreIssues = false;
+                    break;
+                  }
+
+                  for (const issue of issues.data) {
+                    // Skip if the issue has 'good first issue' label
+                    if (issue.labels.some(label => label.name === 'good first issue')) {
+                      console.log(`Skipping issue #${issue.number} as it's marked as 'good first issue'`);
+                      continue;
+                    }
+                    if (new Date(issue.updated_at) < sixtyDaysAgo) {
+                      try {
+                        await github.rest.issues.update({
+                          owner,
+                          repo,
+                          issue_number: issue.number,
+                          state: 'closed',
+                          labels: [...issue.labels.map(l => l.name), 'inactive']
+                        });
+                        await github.rest.issues.createComment({
+                          owner,
+                          repo,
+                          issue_number: issue.number,
+                          body: 'This issue has been automatically closed due to inactivity. Please feel free to reopen it if needed.'
+                        });
+                        console.log(`Closed issue #${issue.number} due to inactivity.`);
+                      } catch (error) {
+                        console.error(`Failed to close issue #${issue.number}: ${error.message}`);
+                      }
+                    } else {
+                      console.log(`Issue #${issue.number} is still active. Stopping processing.`);
+                      hasMoreIssues = false;
+                      break;
+                    }
+                  }
+                  page += 1;
+                } catch (error) {
+                  console.error(`Error fetching issues on page ${page}: ${error.message}`);
+                  hasMoreIssues = false;
+                }
+              }
+              console.log('Finished processing issues');
+            }
+
+            await processIssues();

third_party/sglang/.github/workflows/diffusion-ci-gt-gen.yml

@@ -0,0 +1,115 @@
+name: Diffusion CI Ground Truth Generation
+
+on:
+  workflow_dispatch:
+    inputs:
+      ref:
+        description: 'Git ref to checkout'
+        required: false
+        default: ''
+        type: string
+      case_ids:
+        description: 'Specific case IDs to run (space-separated, optional)'
+        required: false
+        default: ''
+        type: string
+
+concurrency:
+  group: diffusion-ci-gt-gen-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: write
+  actions: read
+
+jobs:
+  multimodal-diffusion-gen-1gpu:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: 1-gpu-h100
+    strategy:
+      matrix:
+        part: [0, 1]
+    timeout-minutes: 150
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Install dependencies
+        run: bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+
+      - name: Generate outputs
+        run: |
+          cd python
+          python -m sglang.multimodal_gen.test.scripts.gen_diffusion_ci_outputs \
+            --suite 1-gpu \
+            --partition-id ${{ matrix.part }} \
+            --total-partitions 2 \
+            --out-dir ./diffusion-ci-outputs \
+            ${{ inputs.case_ids != '' && format('--case-ids {0}', inputs.case_ids) || '' }}
+
+      - name: Upload artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: diffusion-gen-1gpu-part${{ matrix.part }}
+          path: python/diffusion-ci-outputs
+          retention-days: 7
+
+  multimodal-diffusion-gen-2gpu:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: 2-gpu-h100
+    strategy:
+      matrix:
+        part: [0, 1]
+    timeout-minutes: 150
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Install dependencies
+        run: bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+
+      - name: Generate outputs
+        run: |
+          cd python
+          python -m sglang.multimodal_gen.test.scripts.gen_diffusion_ci_outputs \
+            --suite 2-gpu \
+            --partition-id ${{ matrix.part }} \
+            --total-partitions 2 \
+            --out-dir ./diffusion-ci-outputs \
+            ${{ inputs.case_ids != '' && format('--case-ids {0}', inputs.case_ids) || '' }}
+
+      - name: Upload artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: diffusion-gen-2gpu-part${{ matrix.part }}
+          path: python/diffusion-ci-outputs
+          retention-days: 7
+
+  diffusion-ci-push:
+    needs: [multimodal-diffusion-gen-1gpu, multimodal-diffusion-gen-2gpu]
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
+        with:
+          pattern: diffusion-gen-*
+          path: combined
+          merge-multiple: true
+
+      - name: Collect image files
+        run: |
+          mkdir -p gt_images
+          find combined \( -name "*.png" -o -name "*.jpg" -o -name "*.jpeg" -o -name "*.webp" \) -type f -exec cp -f {} gt_images/ \;
+
+      - name: Publish GT images to sglang-bot/sglang-ci-data
+        env:
+          GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
+        run: python scripts/ci/utils/diffusion/publish_diffusion_gt.py --source-dir gt_images

third_party/sglang/.github/workflows/execute-notebook.yml

@@ -0,0 +1,74 @@
+name: Execute Notebooks
+
+on:
+  pull_request:
+    branches: [ main ]
+    types: [opened, synchronize, reopened, labeled]
+    paths:
+      - "python/sglang/**"
+      - "docs/**"
+      - "!python/sglang/**/*.md"
+      - "!docs/**/*.md"
+  workflow_dispatch:
+
+
+concurrency:
+  group: execute-notebook-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  SGLANG_IS_IN_CI: true
+
+jobs:
+  call-gate:
+    # Align with PR Test: fail fast if PR doesn't have run-ci label.
+    # This makes /tag-and-rerun-ci work by rerunning this failed workflow.
+    uses: ./.github/workflows/pr-gate.yml
+    secrets: inherit
+
+  run-all-notebooks:
+    needs: [call-gate]
+    runs-on: 1-gpu-h100
+    if: github.event_name != 'pull_request' || needs.call-gate.result == 'success'
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+          pip install -r docs/requirements.txt
+          apt-get update && apt-get install -y pandoc parallel retry
+          ln -sf "$(which python3)" /usr/bin/python
+
+      - name: Setup Jupyter Kernel
+        run: |
+          python -m ipykernel install --user --name python3 --display-name "Python 3"
+
+      - name: Execute notebooks
+        timeout-minutes: 40
+        run: |
+          cd docs
+          make clean
+          make compile
+
+
+  notebook-finish:
+    needs: [
+      call-gate,
+      run-all-notebooks
+    ]
+    runs-on: ubuntu-latest
+    if: always() && needs.run-all-notebooks.result != 'skipped'
+    steps:
+      - name: Check all dependent job statuses
+        run: |
+          results=(${{ join(needs.*.result, ' ') }})
+          for result in "${results[@]}"; do
+            if [ "$result" = "failure" ] || [ "$result" = "cancelled" ]; then
+              echo "Job failed with result: $result"
+              exit 1
+            fi
+          done
+          echo "All jobs completed successfully"
+          exit 0

third_party/sglang/.github/workflows/full-test-npu.yml

@@ -0,0 +1,355 @@
+name: Full Test (NPU)
+
+on:
+#  pull_request:
+#    branches:
+#      - main
+#    paths:
+#      - ".github/workflows/full-test-npu.yml"
+  workflow_dispatch:
+    inputs:
+      ref:
+        description: 'Git ref (branch, tag, or SHA) to test. If not provided, uses the default branch.'
+        required: false
+        type: string
+        default: ''
+      job_filter:
+        description: 'Select which job to run (leave empty or "all" to run all jobs)'
+        required: false
+        type: string
+        default: 'all'
+      image_a3:
+        description: 'The a3 running docker image of the test task.'
+        required: false
+        type: string
+        default: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11'
+      skip_install_flag:
+        description: 'Indicates whether to skip the installation of sglang, defaulting to false.'
+        required: false
+        type: string
+        default: 'false'
+
+concurrency:
+  group: full-test-npu-${{ inputs.ref || github.ref }}
+  cancel-in-progress: ${{ github.event_name != 'workflow_call' }}
+
+jobs:
+  set-image-config:
+    runs-on: ubuntu-latest
+    outputs:
+      ref: ${{ steps.set-vars.outputs.ref }}
+      job_filter: ${{ steps.set-vars.outputs.job_filter }}
+      image_a3: ${{ steps.set-vars.outputs.image_a3 }}
+      skip_install_flag: ${{ steps.set-vars.outputs.skip_install_flag }}
+    steps:
+      # When triggered by PR, no inputs parameters are used. The latest community code is tested by default.
+      - name: Set image config
+        id: set-vars
+        run: |
+          if [ -z "${{ inputs.ref }}" ]; then
+            echo "ref=" >> $GITHUB_OUTPUT
+          else
+            echo "ref=${{ inputs.ref }}" >> $GITHUB_OUTPUT
+          fi
+
+          if [ -z "${{ inputs.job_filter }}" ]; then
+            echo "job_filter=all" >> $GITHUB_OUTPUT
+          else
+            echo "job_filter=${{ inputs.job_filter }}" >> $GITHUB_OUTPUT
+          fi
+
+          if [ -z "${{ inputs.image_a3 }}" ]; then
+            echo "image_a3=swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11" >> $GITHUB_OUTPUT
+          else
+            echo "image_a3=${{ inputs.image_a3 }}" >> $GITHUB_OUTPUT
+          fi
+
+          if [ -z "${{ inputs.skip_install_flag }}" ]; then
+            echo "skip_install_flag=false" >> $GITHUB_OUTPUT
+          else
+            echo "skip_install_flag=${{ inputs.skip_install_flag }}" >> $GITHUB_OUTPUT
+          fi
+
+  nighly-test-npu:
+    needs: [set-image-config]
+    name: nightly-test-npu
+    if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
+    uses: ./.github/workflows/nightly-test-npu.yml
+    with:
+      ref:  ${{ needs.set-image-config.outputs.ref }}
+      job_filter: ${{ needs.set-image-config.outputs.job_filter }}
+      image_a3: ${{ needs.set-image-config.outputs.image_a3 }}
+      skip_install_flag: ${{ needs.set-image-config.outputs.skip_install_flag }}
+    secrets: inherit
+
+  full-1-npu-a3:
+    needs: [set-image-config]
+    if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
+    runs-on: linux-aarch64-a3-2
+    container:
+      image: ${{ needs.set-image-config.outputs.image_a3 }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
+            bash scripts/ci/npu/npu_ci_install_dependency.sh a3
+          fi
+
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Print Log Information
+        run: |
+          bash scripts/ci/npu/npu_log_print.sh
+
+      - name: Run test
+        timeout-minutes: 240
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          pip install sglang_router
+          hf download lmms-lab/MMMU --repo-type dataset
+          pip install sentence_transformers torchaudio==2.8.0
+          pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
+          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
+          pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.25 numpy==1.26.4 dotenv
+          git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
+          cd ./lmms-eval
+          nohup pip install . > lmmslog.txt 2>&1 &
+          sleep 120
+          export PYTHONPATH=$PYTHONPATH:$(pwd)
+          cd ../
+          cd test
+          python3 run_suite.py --hw npu --suite full-1-npu-a3 --nightly --continue-on-error --timeout-per-file 3600
+
+  full-2-npu-a3:
+    needs: [set-image-config]
+    if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
+    runs-on: linux-aarch64-a3-2
+    container:
+      image: ${{ needs.set-image-config.outputs.image_a3 }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
+            bash scripts/ci/npu/npu_ci_install_dependency.sh a3
+          fi
+
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Print Log Information
+        run: |
+          bash scripts/ci/npu/npu_log_print.sh
+
+      - name: Run test
+        timeout-minutes: 240
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          pip install sglang_router
+          hf download lmms-lab/MMMU --repo-type dataset
+          pip install sentence_transformers torchaudio==2.8.0
+          pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
+          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
+          pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.25 numpy==1.26.4 dotenv
+          git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
+          cd ./lmms-eval
+          nohup pip install . > lmmslog.txt 2>&1 &
+          sleep 120
+          export PYTHONPATH=$PYTHONPATH:$(pwd)
+          cd ../
+          cd test
+          python3 run_suite.py --hw npu --suite full-2-npu-a3 --nightly --continue-on-error --timeout-per-file 3600
+
+  full-4-npu-a3:
+    needs: [set-image-config]
+    if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
+    runs-on: linux-aarch64-a3-4
+    container:
+      image: ${{ needs.set-image-config.outputs.image_a3 }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
+            bash scripts/ci/npu/npu_ci_install_dependency.sh a3
+          fi
+
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Print Log Information
+        run: |
+          bash scripts/ci/npu/npu_log_print.sh
+
+      - name: Run test
+        timeout-minutes: 240
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          pip install sglang_router
+          hf download lmms-lab/MMMU --repo-type dataset
+          pip install sentence_transformers torchaudio==2.8.0
+          pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
+          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
+          pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.25 numpy==1.26.4 dotenv
+          git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
+          cd ./lmms-eval
+          nohup pip install . > lmmslog.txt 2>&1 &
+          sleep 120
+          export PYTHONPATH=$PYTHONPATH:$(pwd)
+          cd ../
+          cd test
+          python3 run_suite.py --hw npu --suite full-4-npu-a3 --nightly --continue-on-error --timeout-per-file 3600
+
+  full-16-npu-a3:
+    needs: [set-image-config]
+    if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
+    runs-on: linux-aarch64-a3-16
+    container:
+      image: ${{ needs.set-image-config.outputs.image_a3 }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
+            bash scripts/ci/npu/npu_ci_install_dependency.sh a3
+          fi
+
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Print Log Information
+        run: |
+          bash scripts/ci/npu/npu_log_print.sh
+
+      - name: Run test
+        timeout-minutes: 240
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          pip install sglang_router
+          hf download lmms-lab/MMMU --repo-type dataset
+          pip install sentence_transformers torchaudio==2.8.0
+          pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
+          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
+          pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.25 numpy==1.26.4 dotenv
+          git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
+          cd ./lmms-eval
+          nohup pip install . > lmmslog.txt 2>&1 &
+          sleep 120
+          export PYTHONPATH=$PYTHONPATH:$(pwd)
+          cd ../
+          cd test
+          python3 run_suite.py --hw npu --suite full-16-npu-a3 --nightly --continue-on-error --timeout-per-file 3600
+
+  check-all-jobs:
+    if: github.repository == 'sgl-project/sglang' && always()
+    needs:
+      - nighly-test-npu
+      - full-1-npu-a3
+      - full-2-npu-a3
+      - full-4-npu-a3
+      - full-16-npu-a3
+    runs-on: ubuntu-latest
+    container:
+      image: docker.m.daocloud.io/ubuntu:22.04
+    steps:
+      - name: Check if any job failed
+        run: |
+          if [[ "${{ 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"

third_party/sglang/.github/workflows/labeler.yml

@@ -0,0 +1,20 @@
+name: Auto Label PRs
+
+on:
+  pull_request_target:
+    types: [opened, synchronize, reopened]
+
+permissions:
+  contents: read
+  pull-requests: write
+
+jobs:
+  label:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Auto-label by file changes
+        uses: actions/labeler@v5
+        with:
+          repo-token: "${{ secrets.GITHUB_TOKEN }}"
+          configuration-path: .github/labeler.yml
+          sync-labels: false

third_party/sglang/.github/workflows/lint.yml

@@ -0,0 +1,39 @@
+name: Lint
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.12"
+
+      - name: Install pre-commit hook
+        run: |
+          python -m pip install pre-commit
+          pre-commit install
+
+      - name: Run pre-commit checks
+        run: SKIP=no-commit-to-branch pre-commit run --all-files --show-diff-on-failure
+
+      - name: Run lychee docs checks (offline references)
+        uses: lycheeverse/lychee-action@8646ba30535128ac92d33dfc9133794bfdd9b411 # v2
+        with:
+          args: --config .github/linters/lychee.toml README.md "docs/**/*.md" "docs/**/*.rst" "docs/**/*.ipynb"
+
+      - name: Run sgl-kernel clang-format checks
+        uses: DoozyX/clang-format-lint-action@v0.20
+        with:
+          source: sgl-kernel
+          extensions: h,c,cpp,hpp,cu,cuh,cc
+          clangFormatVersion: 20
+          style: file

third_party/sglang/.github/workflows/list-active-pr-runs.yml

@@ -0,0 +1,317 @@
+name: List Active Runs
+
+on:
+  workflow_dispatch:
+    inputs:
+      workflows:
+        description: 'Space-separated list of workflow filenames to check'
+        required: false
+        type: string
+        default: 'pr-test.yml'
+
+permissions:
+  actions: read
+  contents: read
+  pull-requests: read
+
+jobs:
+  list-active-runs:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Install GitHub CLI
+        run: sudo apt-get install -y gh jq
+
+      - name: List active runs grouped by PR
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          REPO: ${{ github.repository }}
+          WORKFLOWS: ${{ github.event.inputs.workflows || 'pr-test.yml' }}
+        shell: bash
+        run: |
+          set -euo pipefail
+
+          echo "========================================="
+          echo "🔍 Active Workflow Runs Report"
+          echo "========================================="
+          echo ""
+
+          # Get all workflows or specific ones
+          read -r -a workflow_files <<< "${WORKFLOWS}"
+          echo "📋 Checking specified workflows: ${WORKFLOWS}"
+
+          echo ""
+
+          # Create a temporary file to store PR data
+          pr_data_file=$(mktemp)
+
+          # Process each workflow
+          for workflow_file in ${workflow_files[@]}; do
+            echo "Scanning workflow: $workflow_file"
+
+            # Get all active runs (queued, waiting, in_progress)
+            active_runs=$(gh run list \
+              --repo "$REPO" \
+              --workflow "$workflow_file" \
+              --json databaseId,status,event,headBranch,createdAt,updatedAt,headSha,number,attempt \
+              --limit 500 \
+              | jq -c '.[] | select(.status=="queued" or .status=="waiting" or .status=="in_progress")')
+
+            if [ -z "$active_runs" ]; then
+              continue
+            fi
+
+            # Process each run
+            echo "$active_runs" | while read -r run; do
+              run_id=$(echo "$run" | jq -r '.databaseId')
+              run_status=$(echo "$run" | jq -r '.status')
+              run_event=$(echo "$run" | jq -r '.event')
+              created_at=$(echo "$run" | jq -r '.createdAt')
+              head_sha=$(echo "$run" | jq -r '.headSha')
+              run_number=$(echo "$run" | jq -r '.number')
+              run_attempt=$(echo "$run" | jq -r '.attempt // 1')
+
+              # Get detailed run information including jobs
+              run_details=$(gh api "repos/$REPO/actions/runs/$run_id" 2>/dev/null || true)
+
+              if [ -z "$run_details" ]; then
+                continue
+              fi
+
+              head_owner=$(echo "$run_details" | jq -r '.head_repository.owner.login // empty')
+              head_branch=$(echo "$run_details" | jq -r '.head_branch // empty')
+
+              if [ -z "$head_owner" ] || [ -z "$head_branch" ]; then
+                continue
+              fi
+
+              # Find PR number (may be empty for non-PR runs)
+              pr_number=$(gh api "repos/$REPO/pulls?state=open&head=${head_owner}:${head_branch}" \
+                --jq '.[0].number // empty' 2>/dev/null || true)
+
+              if [ -z "$pr_number" ]; then
+                pr_number="NO_PR"
+              fi
+
+              # Get jobs for this run (with pagination to avoid missing jobs)
+              jobs=$(gh api "repos/$REPO/actions/runs/$run_id/jobs" --paginate --jq '.jobs[]' | jq -s '.')
+
+              running_jobs=$(echo "$jobs" | jq '[.[] | select(.status=="in_progress")] | length')
+              queued_jobs=$(echo "$jobs" | jq '[.[] | select(.status=="queued" or .status=="waiting")] | length')
+
+              # Get runner info for running jobs
+              runners=$(echo "$jobs" | jq -r '.[] | select(.status=="in_progress") | .runner_name // "N/A"' | paste -sd "," -)
+
+              # Calculate queue time
+              current_time=$(date -u +%s)
+              created_time=$(date -u -d "$created_at" +%s 2>/dev/null || echo "$current_time")
+              queue_time=$((current_time - created_time))
+              queue_minutes=$((queue_time / 60))
+
+              # Store data in temporary file (unified format with event and branch)
+              echo "$pr_number|$workflow_file|$run_id|$run_status|$running_jobs|$queued_jobs|$runners|$queue_minutes|$created_at|$head_sha|$run_attempt|$run_event|$head_branch" >> "$pr_data_file"
+            done
+          done
+
+          echo ""
+          echo "========================================="
+          echo "📊 Active Runs Summary"
+          echo "========================================="
+          echo ""
+
+          if [ ! -s "$pr_data_file" ]; then
+            echo "✅ No active runs found"
+            rm -f "$pr_data_file"
+            exit 0
+          fi
+
+          # Get unique PR numbers (exclude NO_PR entries)
+          pr_numbers=$(cut -d'|' -f1 < "$pr_data_file" | grep -v '^NO_PR$' | sort -u || true)
+
+          # Separate high priority and normal PRs
+          high_priority_prs=()
+          normal_prs=()
+
+          for pr_num in $pr_numbers; do
+            labels=$(gh pr view "$pr_num" --repo "$REPO" --json labels \
+              | jq -r '.labels[].name' 2>/dev/null || true)
+
+            if echo "$labels" | grep -Fxq "high priority"; then
+              high_priority_prs+=($pr_num)
+            else
+              normal_prs+=($pr_num)
+            fi
+          done
+
+          # Combine: high priority first, then normal
+          sorted_pr_numbers=("${high_priority_prs[@]}" "${normal_prs[@]}")
+
+          pr_count=0
+          total_running=0
+          total_queued=0
+
+          for pr_num in "${sorted_pr_numbers[@]}"; do
+            pr_count=$((pr_count + 1))
+
+            # Get PR details
+            pr_info=$(gh pr view "$pr_num" --repo "$REPO" --json title,author,labels,url 2>/dev/null || true)
+
+            if [ -z "$pr_info" ]; then
+              continue
+            fi
+
+            pr_title=$(echo "$pr_info" | jq -r '.title')
+            pr_author=$(echo "$pr_info" | jq -r '.author.login')
+            pr_url=$(echo "$pr_info" | jq -r '.url')
+            pr_labels=$(echo "$pr_info" | jq -r '.labels[].name' | paste -sd ", " -)
+
+            if [ -z "$pr_labels" ]; then
+              pr_labels="(no labels)"
+            fi
+
+            # Add priority indicator
+            priority_indicator=""
+            if echo "$pr_labels" | grep -q "high priority"; then
+              priority_indicator="🔴 [HIGH PRIORITY] "
+            fi
+
+            echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+            echo "🔗 ${priority_indicator}PR #$pr_num: $pr_title"
+            echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+            echo "👤 Author: $pr_author"
+            echo "🏷️  Labels: $pr_labels"
+            echo "🔗 URL: $pr_url"
+            echo ""
+
+            # Get all runs for this PR
+            pr_runs=$(grep "^$pr_num|" "$pr_data_file")
+
+            pr_running_total=0
+            pr_queued_total=0
+
+            echo "$pr_runs" | while read -r line; do
+              workflow=$(echo "$line" | cut -d'|' -f2)
+              run_id=$(echo "$line" | cut -d'|' -f3)
+              status=$(echo "$line" | cut -d'|' -f4)
+              running=$(echo "$line" | cut -d'|' -f5)
+              queued=$(echo "$line" | cut -d'|' -f6)
+              runners=$(echo "$line" | cut -d'|' -f7)
+              queue_min=$(echo "$line" | cut -d'|' -f8)
+              created=$(echo "$line" | cut -d'|' -f9)
+              attempt=$(echo "$line" | cut -d'|' -f11)
+
+              pr_running_total=$((pr_running_total + running))
+              pr_queued_total=$((pr_queued_total + queued))
+
+              run_url="https://github.com/$REPO/actions/runs/$run_id"
+
+              # Calculate retry count for this specific run
+              retry_count=$((attempt - 1))
+
+              # Show retry indicator
+              retry_indicator=""
+              if [ "$retry_count" -gt 0 ]; then
+                retry_indicator=" 🔄 Retry #$retry_count"
+              fi
+
+              echo "  📦 Workflow: $workflow (Run #$run_id)$retry_indicator"
+              echo "     Status: $status"
+              echo "     🟢 Running jobs: $running"
+              echo "     🟡 Queued jobs: $queued"
+
+              if [ "$running" -gt 0 ] && [ "$runners" != "" ]; then
+                echo "     🖥️  Runners: $runners"
+              fi
+
+              if [ "$queue_min" -gt 0 ]; then
+                echo "     ⏱️  Queue time: ${queue_min} minutes"
+              fi
+
+              echo "     🔗 Run URL: $run_url"
+              echo ""
+            done
+
+            # Summary for this PR
+            pr_running_total=$(grep "^$pr_num|" "$pr_data_file" | cut -d'|' -f5 | awk '{sum+=$1} END {print sum+0}')
+            pr_queued_total=$(grep "^$pr_num|" "$pr_data_file" | cut -d'|' -f6 | awk '{sum+=$1} END {print sum+0}')
+
+            total_running=$((total_running + pr_running_total))
+            total_queued=$((total_queued + pr_queued_total))
+
+            echo "  📊 PR Total: $pr_running_total running, $pr_queued_total queued"
+            echo ""
+          done
+
+          # --- Non-PR Runs Section ---
+          non_pr_runs=$(grep '^NO_PR|' "$pr_data_file" 2>/dev/null || true)
+          non_pr_running=0
+          non_pr_queued=0
+
+          if [ -n "$non_pr_runs" ]; then
+            echo "========================================="
+            echo "📦 Non-PR Runs (manual / scheduled / other)"
+            echo "========================================="
+            echo ""
+
+            echo "$non_pr_runs" | while read -r line; do
+              workflow=$(echo "$line" | cut -d'|' -f2)
+              run_id=$(echo "$line" | cut -d'|' -f3)
+              status=$(echo "$line" | cut -d'|' -f4)
+              running=$(echo "$line" | cut -d'|' -f5)
+              queued=$(echo "$line" | cut -d'|' -f6)
+              runners=$(echo "$line" | cut -d'|' -f7)
+              queue_min=$(echo "$line" | cut -d'|' -f8)
+              created=$(echo "$line" | cut -d'|' -f9)
+              attempt=$(echo "$line" | cut -d'|' -f11)
+              event=$(echo "$line" | cut -d'|' -f12)
+              branch=$(echo "$line" | cut -d'|' -f13)
+
+              run_url="https://github.com/$REPO/actions/runs/$run_id"
+
+              retry_count=$((attempt - 1))
+              retry_indicator=""
+              if [ "$retry_count" -gt 0 ]; then
+                retry_indicator=" 🔄 Retry #$retry_count"
+              fi
+
+              echo "  📦 Workflow: $workflow (Run #$run_id)$retry_indicator"
+              echo "     Event: $event"
+              echo "     Branch: $branch"
+              echo "     Status: $status"
+              echo "     🟢 Running jobs: $running"
+              echo "     🟡 Queued jobs: $queued"
+
+              if [ "$running" -gt 0 ] && [ "$runners" != "" ]; then
+                echo "     🖥️  Runners: $runners"
+              fi
+
+              if [ "$queue_min" -gt 0 ]; then
+                echo "     ⏱️  Queue time: ${queue_min} minutes"
+              fi
+
+              echo "     🔗 Run URL: $run_url"
+              echo ""
+            done
+
+            non_pr_running=$(echo "$non_pr_runs" | cut -d'|' -f5 | awk '{sum+=$1} END {print sum+0}')
+            non_pr_queued=$(echo "$non_pr_runs" | cut -d'|' -f6 | awk '{sum+=$1} END {print sum+0}')
+            non_pr_count=$(echo "$non_pr_runs" | wc -l | tr -d ' ')
+
+            total_running=$((total_running + non_pr_running))
+            total_queued=$((total_queued + non_pr_queued))
+
+            echo "  📊 Non-PR Total: $non_pr_running running, $non_pr_queued queued"
+            echo ""
+          fi
+
+          # Overall summary
+          echo "========================================="
+          echo "📈 Overall Summary"
+          echo "========================================="
+          echo "Total PRs with active runs: $pr_count"
+          echo "Total non-PR active runs: ${non_pr_count:-0}"
+          echo "Total running jobs: $total_running"
+          echo "Total queued jobs: $total_queued"
+          echo "========================================="
+
+          # Cleanup
+          rm -f "$pr_data_file"

third_party/sglang/.github/workflows/nightly-link-check.yml

@@ -0,0 +1,32 @@
+name: Nightly Link Check
+
+on:
+  schedule:
+    - cron: "0 2 * * *"
+  workflow_dispatch:
+
+concurrency:
+  group: nightly-link-check-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  lychee-online:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: ubuntu-latest
+    timeout-minutes: 20
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Run lychee online link checks
+        uses: lycheeverse/lychee-action@8646ba30535128ac92d33dfc9133794bfdd9b411 # v2
+        with:
+          fail: true
+          args: >-
+            --config .github/linters/lychee-ci.toml
+            README.md
+            docs/**/*.md
+            docs/**/*.rst
+            docs/**/*.ipynb
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

third_party/sglang/.github/workflows/nightly-release-gateway.yml

@@ -0,0 +1,196 @@
+# Nightly release workflow for SGLang Model Gateway
+
+name: Nightly Release SGLang Model Gateway to PyPI
+
+on:
+  schedule:
+    # Run at 2 AM UTC every day
+    - cron: '0 2 * * *'
+  workflow_dispatch:  # Allow manual trigger
+
+jobs:
+  build:
+    name: build on ${{ matrix.platform || matrix.os }} (${{ matrix.target }} - ${{ matrix.manylinux || 'auto' }})
+    runs-on: ${{ matrix.os }}-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu, macos, windows]
+        target: [x86_64, aarch64]
+        manylinux: [auto]
+        include:
+          - os: ubuntu
+            platform: linux
+          - os: windows
+            ls: dir
+            target: x86_64
+            python-architecture: x64
+            interpreter: 3.9 3.10 3.11 3.12 3.13
+          - os: macos
+            target: aarch64
+            interpreter: 3.9 3.10 3.11 3.12 3.13
+          - os: ubuntu
+            platform: linux
+            target: aarch64
+          # musllinux
+          - os: ubuntu
+            platform: linux
+            target: x86_64
+            manylinux: musllinux_1_1
+          - os: ubuntu
+            platform: linux
+            target: aarch64
+            manylinux: musllinux_1_1
+        exclude:
+          - os: windows
+            target: aarch64
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          path: sglang-repo
+
+      - name: Move sgl-model-gateway folder to root and delete sglang-repo
+        run: |
+          mv sglang-repo/sgl-model-gateway/* .
+          rm -rf sglang-repo
+          ls -alt
+        shell: bash
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.13"
+          architecture: ${{ matrix.python-architecture || 'x64' }}
+
+      - name: Modify version for nightly release
+        run: |
+          # Get current version from pyproject.toml
+          CURRENT_VERSION=$(python -c "import tomllib; print(tomllib.load(open('bindings/python/pyproject.toml', 'rb'))['project']['version'])" 2>/dev/null || python -c "import tomli; print(tomli.load(open('bindings/python/pyproject.toml', 'rb'))['project']['version'])")
+          # Create nightly version with date: e.g., 0.2.1.dev20250128
+          NIGHTLY_VERSION="${CURRENT_VERSION}.dev$(date +%Y%m%d)"
+          echo "Nightly version: $NIGHTLY_VERSION"
+
+          # Update pyproject.toml with nightly version (temporary, not committed)
+          sed -i.bak "s/version = \"${CURRENT_VERSION}\"/version = \"${NIGHTLY_VERSION}\"/" bindings/python/pyproject.toml
+
+          # Verify the change
+          cat bindings/python/pyproject.toml | grep "^version"
+        shell: bash
+
+      - name: Install twine and tomli
+        run: pip install -U twine tomli
+
+      - name: Install protoc (macOS)
+        if: matrix.os == 'macos'
+        run: brew install protobuf
+
+      - name: Install protoc (Windows)
+        if: matrix.os == 'windows'
+        run: choco install protoc -y
+
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          working-directory: bindings/python
+          target: ${{ matrix.target }}
+          manylinux: ${{ matrix.manylinux || 'auto' }}
+          args: --release --out dist --features vendored-openssl --interpreter ${{ matrix.interpreter || '3.9 3.10 3.11 3.12 3.13 3.14' }}
+          rust-toolchain: stable
+          docker-options: -e CI -e CC_aarch64_unknown_linux_gnu=aarch64-linux-gnu-gcc -e CXX_aarch64_unknown_linux_gnu=aarch64-linux-gnu-g++
+          before-script-linux: |
+            # Install build dependencies (perl/make for vendored OpenSSL, protoc for gRPC)
+            if command -v yum &> /dev/null; then
+              yum update -y && yum install -y wget unzip gcc gcc-c++ perl-core make
+              # Install cross-compilation toolchain for aarch64 if needed
+              if [ "${{ matrix.target }}" = "aarch64" ]; then
+                yum install -y gcc-aarch64-linux-gnu gcc-c++-aarch64-linux-gnu || true
+              fi
+            elif command -v apt-get &> /dev/null; then
+              apt-get update && apt-get install -y wget unzip gcc g++ perl make
+              # Install cross-compilation toolchain for aarch64 if needed
+              if [ "${{ matrix.target }}" = "aarch64" ]; then
+                apt-get install -y gcc-aarch64-linux-gnu g++-aarch64-linux-gnu || true
+              fi
+            fi
+            (cd /tmp && \
+             wget https://github.com/protocolbuffers/protobuf/releases/download/v32.0/protoc-32.0-linux-x86_64.zip && \
+             unzip protoc-32.0-linux-x86_64.zip -d /usr/local && \
+             rm protoc-32.0-linux-x86_64.zip)
+            protoc --version
+
+      - name: List built packages
+        run: ${{ matrix.ls || 'ls -lh' }} bindings/python/dist/
+
+      - name: Check packages
+        run: twine check --strict bindings/python/dist/*
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: packages-${{ matrix.os }}-${{ matrix.target }}-${{ matrix.manylinux || 'auto' }}
+          path: bindings/python/dist/
+
+  build-sdist:
+    name: Build SDist
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          path: sglang-repo
+
+      - name: Move sgl-model-gateway folder to root and delete sglang-repo
+        run: |
+          mv sglang-repo/sgl-model-gateway/* .
+          rm -rf sglang-repo
+          ls -alt
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.13"
+
+      - name: Modify version for nightly release
+        run: |
+          # Get current version from pyproject.toml
+          CURRENT_VERSION=$(python -c "import tomllib; print(tomllib.load(open('bindings/python/pyproject.toml', 'rb'))['project']['version'])" 2>/dev/null || python -c "import tomli; print(tomli.load(open('bindings/python/pyproject.toml', 'rb'))['project']['version'])")
+          # Create nightly version with date: e.g., 0.2.1.dev20250128
+          NIGHTLY_VERSION="${CURRENT_VERSION}.dev$(date +%Y%m%d)"
+          echo "Nightly version: $NIGHTLY_VERSION"
+
+          # Update pyproject.toml with nightly version (temporary, not committed)
+          sed -i "s/version = \"${CURRENT_VERSION}\"/version = \"${NIGHTLY_VERSION}\"/" bindings/python/pyproject.toml
+
+          # Verify the change
+          cat bindings/python/pyproject.toml | grep "^version"
+
+      - name: Build SDist
+        uses: PyO3/maturin-action@v1
+        with:
+          working-directory: bindings/python
+          command: sdist
+          args: --out dist
+          rust-toolchain: stable
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: sdist
+          path: bindings/python/dist/*.tar.gz
+
+  upload:
+    name: Upload to TestPyPI
+    if: github.repository == 'sgl-project/sglang'  # Ensure this job only runs for the sgl-project/sglang repository
+    needs: [build, build-sdist]
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          path: dist
+          merge-multiple: true
+
+      - name: Upload to TestPyPI
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.TEST_PYPI_TOKEN_ROUTER }}
+        run: |
+          pip install twine
+          twine upload --repository testpypi dist/* --verbose

third_party/sglang/.github/workflows/nightly-test-intel.yml

@@ -0,0 +1,33 @@
+name: Nightly Test (Intel)
+
+on:
+  schedule:
+    - cron: '0 0 * * *'
+  push:
+    branches:
+      - main
+    paths:
+      - "python/sglang/version.py"
+  workflow_dispatch:
+  workflow_call:
+    inputs:
+      ref:
+        description: "Branch, tag or SHA to checkout"
+        required: false
+        type: string
+        default: ""
+
+concurrency:
+  group: nightly-test-intel-${{ inputs.ref || github.ref }}
+  cancel-in-progress: ${{ github.event_name != 'workflow_call' }}
+
+jobs:
+  # Placeholder for Intel GPU tests
+  # Add Intel-specific nightly test workflows here when available
+
+  placeholder:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Placeholder
+        run: echo "Intel nightly tests will be added here"

third_party/sglang/.github/workflows/nightly-test-npu.yml

@@ -0,0 +1,428 @@
+name: Nightly Test (NPU)
+
+on:
+  schedule:
+    - cron: '0 18 * * *'  # Execute at 2:00 a.m. Beijing Time every day
+  pull_request:
+    branches:
+      - main
+    paths:
+      - ".github/workflows/nightly-test-npu.yml"
+  workflow_dispatch:
+  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: ''
+      job_filter:
+        description: 'Select which job to run (leave empty or "all" to run all jobs)'
+        required: false
+        type: string
+        default: 'all'
+      image_a3:
+        description: 'The a3 running docker image of the test task.'
+        required: false
+        type: string
+        default: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11'
+      skip_install_flag:
+        description: 'Indicates whether to skip the installation of sglang, defaulting to false.'
+        required: false
+        type: string
+        default: 'false'
+
+
+concurrency:
+  group: nightly-test-npu-${{ inputs.ref || github.ref }}
+  cancel-in-progress: ${{ github.event_name != 'workflow_call' }}
+
+jobs:
+  set-image-config:
+    runs-on: ubuntu-latest
+    outputs:
+      ref: ${{ steps.set-vars.outputs.ref }}
+      job_filter: ${{ steps.set-vars.outputs.job_filter }}
+      image_a3: ${{ steps.set-vars.outputs.image_a3 }}
+      skip_install_flag: ${{ steps.set-vars.outputs.skip_install_flag }}
+    steps:
+      # When triggered by PR, no inputs parameters are used. The latest community code is tested by default.
+      - name: Set image config
+        id: set-vars
+        run: |
+          if [ -z "${{ inputs.ref }}" ]; then
+            echo "ref=" >> $GITHUB_OUTPUT
+          else
+            echo "ref=${{ inputs.ref }}" >> $GITHUB_OUTPUT
+          fi
+
+          if [ -z "${{ inputs.job_filter }}" ]; then
+            echo "job_filter=all" >> $GITHUB_OUTPUT
+          else
+            echo "job_filter=${{ inputs.job_filter }}" >> $GITHUB_OUTPUT
+          fi
+
+          if [ -z "${{ inputs.image_a3 }}" ]; then
+            echo "image_a3=swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11" >> $GITHUB_OUTPUT
+          else
+            echo "image_a3=${{ inputs.image_a3 }}" >> $GITHUB_OUTPUT
+          fi
+
+          if [ -z "${{ inputs.skip_install_flag }}" ]; then
+            echo "skip_install_flag=false" >> $GITHUB_OUTPUT
+          else
+            echo "skip_install_flag=${{ inputs.skip_install_flag }}" >> $GITHUB_OUTPUT
+          fi
+
+  nightly-1-npu-a3:
+    needs: [set-image-config]
+    if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
+    runs-on: linux-aarch64-a3-2
+    strategy:
+      fail-fast: false
+      matrix:
+        part: [0, 1]
+    container:
+      image: ${{ needs.set-image-config.outputs.image_a3 }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
+            bash scripts/ci/npu/npu_ci_install_dependency.sh a3
+          fi
+
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Print Log Information
+        run: |
+          bash scripts/ci/npu/npu_log_print.sh
+
+      - name: Run test
+        timeout-minutes: 240
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          pip install sglang_router
+          hf download lmms-lab/MMMU --repo-type dataset
+          pip install sentence_transformers torchaudio==2.8.0
+          pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
+          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
+          pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.32 numpy==1.26.4 dotenv
+          git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
+          cd ./lmms-eval
+          nohup pip install . > lmmslog.txt 2>&1 &
+          sleep 120
+          export PYTHONPATH=$PYTHONPATH:$(pwd)
+          cd ../
+          cd test
+          python3 run_suite.py --hw npu --suite nightly-1-npu-a3 --nightly --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
+
+  nightly-2-npu-a3:
+    needs: [set-image-config]
+    if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
+    runs-on: linux-aarch64-a3-2
+    strategy:
+      fail-fast: false
+      matrix:
+        part: [0]
+    container:
+      image: ${{ needs.set-image-config.outputs.image_a3 }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
+            bash scripts/ci/npu/npu_ci_install_dependency.sh a3
+          fi
+
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Print Log Information
+        run: |
+          bash scripts/ci/npu/npu_log_print.sh
+      - name: Run test
+        timeout-minutes: 240
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          pip install sglang_router
+          hf download lmms-lab/MMMU --repo-type dataset
+          pip install sentence_transformers torchaudio==2.8.0
+          pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
+          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
+          pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.32 numpy==1.26.4 dotenv
+          git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
+          cd ./lmms-eval
+          nohup pip install . > lmmslog.txt 2>&1 &
+          sleep 120
+          export PYTHONPATH=$PYTHONPATH:$(pwd)
+          cd ../
+          cd test
+          python3 run_suite.py --hw npu --suite nightly-2-npu-a3 --nightly --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 1
+
+  nightly-4-npu-a3:
+    needs: [set-image-config]
+    if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
+    runs-on: linux-aarch64-a3-4
+    strategy:
+      fail-fast: false
+      matrix:
+        part: [0]
+    container:
+      image: ${{ needs.set-image-config.outputs.image_a3 }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ needs.set-image-config.outputs.ref|| github.ref }}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
+            bash scripts/ci/npu/npu_ci_install_dependency.sh a3
+          fi
+
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Print Log Information
+        run: |
+          bash scripts/ci/npu/npu_log_print.sh
+
+      - name: Run test
+        timeout-minutes: 240
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          pip install sglang_router
+          hf download lmms-lab/MMMU --repo-type dataset
+          pip install sentence_transformers torchaudio==2.8.0
+          pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
+          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
+          pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.32 numpy==1.26.4 dotenv
+          git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
+          cd ./lmms-eval
+          nohup pip install . > lmmslog.txt 2>&1 &
+          sleep 120
+          export PYTHONPATH=$PYTHONPATH:$(pwd)
+          cd ../
+          cd test
+          python3 run_suite.py --hw npu --suite nightly-4-npu-a3 --nightly --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 1
+
+  nightly-8-npu-a3:
+    needs: [set-image-config]
+    if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
+    runs-on: linux-aarch64-a3-8
+    strategy:
+      fail-fast: false
+      matrix:
+        part: [0]
+    container:
+      image: ${{ needs.set-image-config.outputs.image_a3 }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
+            bash scripts/ci/npu/npu_ci_install_dependency.sh a3
+          fi
+
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Print Log Information
+        run: |
+          bash scripts/ci/npu/npu_log_print.sh
+
+      - name: Run test
+        timeout-minutes: 240
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          pip install sglang_router
+          hf download lmms-lab/MMMU --repo-type dataset
+          pip install sentence_transformers torchaudio==2.8.0
+          pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
+          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
+          pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.32 numpy==1.26.4 dotenv
+          git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
+          cd ./lmms-eval
+          nohup pip install . > lmmslog.txt 2>&1 &
+          sleep 120
+          export PYTHONPATH=$PYTHONPATH:$(pwd)
+          cd ../
+          cd test
+          python3 run_suite.py --hw npu --suite nightly-8-npu-a3 --nightly --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 1
+
+  nightly-16-npu-a3:
+    needs: [set-image-config]
+    if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
+    runs-on: linux-aarch64-a3-16
+    strategy:
+      fail-fast: false
+      matrix:
+        part: [0, 1]
+    container:
+      image: ${{ needs.set-image-config.outputs.image_a3 }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
+            bash scripts/ci/npu/npu_ci_install_dependency.sh a3
+          fi
+
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Print Log Information
+        run: |
+          bash scripts/ci/npu/npu_log_print.sh
+
+      - name: Run test
+        timeout-minutes: 240
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          pip install sglang_router
+          hf download lmms-lab/MMMU --repo-type dataset
+          pip install sentence_transformers torchaudio==2.8.0
+          pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
+          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
+          pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.32 numpy==1.26.4 dotenv
+          git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
+          cd ./lmms-eval
+          nohup pip install . > lmmslog.txt 2>&1 &
+          sleep 120
+          export PYTHONPATH=$PYTHONPATH:$(pwd)
+          cd ../
+          cd test
+          python3 run_suite.py --hw npu --suite nightly-16-npu-a3 --nightly --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
+
+  check-all-jobs:
+    if: github.repository == 'sgl-project/sglang' && always()
+    needs:
+      - nightly-1-npu-a3
+      - nightly-2-npu-a3
+      - nightly-4-npu-a3
+      - nightly-8-npu-a3
+      - nightly-16-npu-a3
+    runs-on: ubuntu-latest
+    container:
+      image: docker.m.daocloud.io/ubuntu:22.04
+    steps:
+      - name: Check if any job failed
+        run: |
+          if [[ "${{ 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"

third_party/sglang/.github/workflows/nightly-test-nvidia.yml

@@ -0,0 +1,796 @@
+name: Nightly Test (Nvidia)
+
+on:
+  schedule:
+    - cron: '0 0 * * *'
+  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'
+          - 'nightly-test-general-1-gpu-h100'
+          - 'nightly-test-general-4-gpu-h100'
+          - 'nightly-test-general-8-gpu-h200'
+          - 'nightly-test-general-8-gpu-h20'
+          - 'nightly-test-general-8-gpu-b200'
+          - 'nightly-test-text-accuracy-2-gpu-h100'
+          - 'nightly-test-text-perf-2-gpu-h100'
+          - 'nightly-test-vlm-accuracy-2-gpu-h100'
+          - 'nightly-test-vlm-perf-2-gpu-h100'
+          - 'nightly-test-multimodal-server-1-gpu'
+          - 'nightly-test-multimodal-server-2-gpu'
+          - 'nightly-test-perf-4-gpu-b200'
+          - 'nightly-test-perf-8-gpu-b200'
+          - 'nightly-test-specialized-8-gpu-b200'
+          - 'nightly-test-kernel-1-gpu-h100'
+          - 'nightly-test-diffusion-comparison'
+          - 'nightly-test-kernel-8-gpu-h200'
+  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: ''
+      job_filter:
+        description: 'Select which job to run (leave empty or "all" to run all jobs)'
+        required: false
+        type: string
+        default: 'all'
+
+concurrency:
+  group: nightly-test-nvidia-${{ inputs.ref || github.ref }}
+  cancel-in-progress: ${{ github.event_name != 'workflow_call' }}
+
+env:
+  SGLANG_IS_IN_CI: true
+  SGLANG_CUDA_COREDUMP: "1"
+  HF_HUB_DOWNLOAD_TIMEOUT: 300
+  HF_HUB_ETAG_TIMEOUT: 300
+
+jobs:
+  # General tests - 1 GPU
+  nightly-test-general-1-gpu-h100:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-1-gpu-h100')
+    runs-on: 1-gpu-h100
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run test
+        timeout-minutes: 60
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite nightly-1-gpu --nightly --continue-on-error
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+
+  # JIT kernel full unit tests (expanded parameter ranges via SGLANG_JIT_KERNEL_RUN_FULL_TESTS)
+  nightly-test-kernel-1-gpu-h100:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-kernel-1-gpu-h100')
+    runs-on: 1-gpu-h100
+    timeout-minutes: 240
+    env:
+      # Full jit_kernel test grids (see sglang.jit_kernel.utils.should_run_full_tests)
+      SGLANG_JIT_KERNEL_RUN_FULL_TESTS: "1"
+      # Match pr-test-jit-kernel workflow for consistent JIT warmup behavior
+      SGLANG_JIT_DEEPGEMM_FAST_WARMUP: true
+      # Allow maintenance bypass on default branch (same semantics as PR JIT workflow)
+      SGLANG_PR_TEST_BYPASS_MAINTENANCE_ON_MAIN: ${{ github.ref == 'refs/heads/main' && 'true' || 'false' }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run jit kernel nightly suite
+        timeout-minutes: 60
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite nightly-kernel-1-gpu --nightly --continue-on-error
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+
+  nightly-test-kernel-8-gpu-h200:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-kernel-8-gpu-h200')
+    runs-on: 8-gpu-h200
+    timeout-minutes: 240
+    env:
+      SGLANG_JIT_KERNEL_RUN_FULL_TESTS: "1"
+      SGLANG_JIT_DEEPGEMM_FAST_WARMUP: true
+      SGLANG_PR_TEST_BYPASS_MAINTENANCE_ON_MAIN: ${{ github.ref == 'refs/heads/main' && 'true' || 'false' }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run multi-GPU jit kernel nightly suite
+        timeout-minutes: 90
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite nightly-kernel-8-gpu-h200 --nightly --continue-on-error
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+
+  # General tests - 4 GPU H100
+  nightly-test-general-4-gpu-h100:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-4-gpu-h100')
+    runs-on: 4-gpu-h100
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run test
+        timeout-minutes: 30
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite nightly-4-gpu --nightly --continue-on-error
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+
+  # General tests - 8 GPU H200
+  nightly-test-general-8-gpu-h200:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-8-gpu-h200')
+    runs-on: 8-gpu-h200
+    strategy:
+      fail-fast: false
+      matrix:
+        partition: [0, 1, 2, 3]
+    env:
+      RUNNER_LABELS: 8-gpu-h200
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run common 8-GPU model tests
+        if: always()
+        timeout-minutes: 300
+        env:
+          TRACE_BASE_URL: https://raw.githubusercontent.com/sglang-bot/sglang-ci-data/main/traces/${{ github.run_id }}
+          PERFETTO_RELAY_URL: ${{ vars.PERFETTO_RELAY_URL }}
+          GPU_CONFIG: "8-gpu-h200"
+          IS_H200: "1"
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite nightly-8-gpu-common --nightly --timeout-per-file=18000 --continue-on-error --auto-partition-id=${{ matrix.partition }} --auto-partition-size=4
+
+      - name: Publish traces to storage repo
+        if: always()
+        continue-on-error: true
+        env:
+          GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
+          GITHUB_RUN_ID: ${{ github.run_id }}
+          GITHUB_RUN_NUMBER: ${{ github.run_number }}
+        run: |
+          TRACE_ARGS=""
+          for dir in test/performance_profiles_*/; do
+            [ -d "$dir" ] && TRACE_ARGS="$TRACE_ARGS --traces-dir $dir"
+          done
+          if [ -n "$TRACE_ARGS" ]; then
+            python3 scripts/ci/utils/publish_traces.py $TRACE_ARGS
+            find test/performance_profiles_*/ -name '*.json.gz' -delete
+          else
+            echo "No trace directories found, skipping publish"
+          fi
+
+      - name: Run test
+        timeout-minutes: 30
+        env:
+          GPU_CONFIG: "8-gpu-h200"
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite nightly-8-gpu-h200 --nightly --continue-on-error
+
+      - name: Collect performance metrics
+        if: always()
+        run: |
+          python3 scripts/ci/utils/save_metrics.py \
+            --gpu-config 8-gpu-h200 \
+            --partition ${{ matrix.partition }} \
+            --run-id ${{ github.run_id }} \
+            --output test/metrics-8gpu-h200-partition-${{ matrix.partition }}.json \
+            --search-dir test/performance_profiles_8_gpu \
+            --search-dir test
+
+      - name: Upload partition metrics
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: metrics-8gpu-h200-partition-${{ matrix.partition }}
+          path: test/metrics-8gpu-h200-partition-${{ matrix.partition }}.json
+          retention-days: 5
+          if-no-files-found: ignore
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+        with:
+          artifact-suffix: ${{ matrix.partition }}
+
+  # General tests - 8 GPU H20
+  nightly-test-general-8-gpu-h20:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-8-gpu-h20')
+    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
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run test
+        timeout-minutes: 30
+        env:
+          GPU_CONFIG: "8-gpu-h20"
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite nightly-8-gpu-h20 --nightly --continue-on-error
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+
+  # General tests - 8 GPU B200
+  nightly-test-general-8-gpu-b200:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-8-gpu-b200')
+    runs-on: 8-gpu-b200
+    strategy:
+      fail-fast: false
+      matrix:
+        partition: [0, 1, 2, 3]
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run common 8-GPU model tests
+        if: always()
+        timeout-minutes: 300
+        env:
+          TRACE_BASE_URL: https://raw.githubusercontent.com/sglang-bot/sglang-ci-data/main/traces/${{ github.run_id }}
+          PERFETTO_RELAY_URL: ${{ vars.PERFETTO_RELAY_URL }}
+          GPU_CONFIG: "8-gpu-b200"
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite nightly-8-gpu-common --nightly --timeout-per-file=12000 --continue-on-error --auto-partition-id=${{ matrix.partition }} --auto-partition-size=4
+
+      - name: Publish traces to storage repo
+        if: always()
+        continue-on-error: true
+        env:
+          GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
+          GITHUB_RUN_ID: ${{ github.run_id }}
+          GITHUB_RUN_NUMBER: ${{ github.run_number }}
+        run: |
+          TRACE_ARGS=""
+          for dir in test/performance_profiles_*/; do
+            [ -d "$dir" ] && TRACE_ARGS="$TRACE_ARGS --traces-dir $dir"
+          done
+          if [ -n "$TRACE_ARGS" ]; then
+            python3 scripts/ci/utils/publish_traces.py $TRACE_ARGS
+            find test/performance_profiles_*/ -name '*.json.gz' -delete
+          else
+            echo "No trace directories found, skipping publish"
+          fi
+
+      - name: Collect performance metrics
+        if: always()
+        run: |
+          python3 scripts/ci/utils/save_metrics.py \
+            --gpu-config 8-gpu-b200 \
+            --partition ${{ matrix.partition }} \
+            --run-id ${{ github.run_id }} \
+            --output test/metrics-8gpu-b200-partition-${{ matrix.partition }}.json \
+            --search-dir test/performance_profiles_8_gpu \
+            --search-dir test
+
+      - name: Upload partition metrics
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: metrics-8gpu-b200-partition-${{ matrix.partition }}
+          path: test/metrics-8gpu-b200-partition-${{ matrix.partition }}.json
+          retention-days: 5
+          if-no-files-found: ignore
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+        with:
+          artifact-suffix: ${{ matrix.partition }}
+
+  # Text model accuracy tests
+  nightly-test-text-accuracy-2-gpu-h100:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-text-accuracy-2-gpu-h100')
+    runs-on: 2-gpu-h100
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run eval test for text models
+        timeout-minutes: 120
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite nightly-eval-text-2-gpu --nightly --continue-on-error --timeout-per-file 4500
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+
+  # Text model performance tests
+  nightly-test-text-perf-2-gpu-h100:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-text-perf-2-gpu-h100')
+    runs-on: 2-gpu-h100
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run performance test for text models
+        timeout-minutes: 180
+        env:
+          TRACE_BASE_URL: https://raw.githubusercontent.com/sglang-bot/sglang-ci-data/main/traces/${{ github.run_id }}
+          PERFETTO_RELAY_URL: ${{ vars.PERFETTO_RELAY_URL }}
+          GPU_CONFIG: "2-gpu-h100"
+        run: |
+          cd test
+          rm -rf performance_profiles_text_models/
+          python3 run_suite.py --hw cuda --suite nightly-perf-text-2-gpu --nightly --continue-on-error --timeout-per-file 3600
+
+      - 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/utils/publish_traces.py --traces-dir test/performance_profiles_text_models
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+
+  # VLM accuracy tests
+  nightly-test-vlm-accuracy-2-gpu-h100:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-vlm-accuracy-2-gpu-h100')
+    runs-on: 2-gpu-h100
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run eval test for VLM models (fixed MMMU-100)
+        timeout-minutes: 240
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite nightly-eval-vlm-2-gpu --nightly --continue-on-error --timeout-per-file 9000
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+
+  # VLM performance tests
+  nightly-test-vlm-perf-2-gpu-h100:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-vlm-perf-2-gpu-h100')
+    runs-on: 2-gpu-h100
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run perf test for VLM models (MMMU)
+        timeout-minutes: 240
+        env:
+          TRACE_BASE_URL: https://raw.githubusercontent.com/sglang-bot/sglang-ci-data/main/traces/${{ github.run_id }}
+          PERFETTO_RELAY_URL: ${{ vars.PERFETTO_RELAY_URL }}
+          GPU_CONFIG: "2-gpu-h100"
+        run: |
+          cd test
+          rm -rf performance_profiles_vlms/
+          python3 run_suite.py --hw cuda --suite nightly-perf-vlm-2-gpu --nightly --continue-on-error --timeout-per-file 3600
+
+      - 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/utils/publish_traces.py --traces-dir test/performance_profiles_vlms
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+
+  # diffusion performance tests
+  nightly-test-multimodal-server-1-gpu:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-multimodal-server-1-gpu')
+    runs-on: 1-gpu-h100
+    strategy:
+      fail-fast: false
+      max-parallel: 5
+      matrix:
+        part: [0, 1]
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+          pip install slack_sdk
+
+      - name: Run diffusion server tests
+        env:
+          SGLANG_DIFFUSION_SLACK_TOKEN: ${{ secrets.SGLANG_DIFFUSION_SLACK_TOKEN }}
+          GITHUB_RUN_ID: ${{ github.run_id }}
+          GPU_CONFIG: "1-gpu-h100"
+
+        timeout-minutes: 90
+        run: |
+          cd python
+          python3 sglang/multimodal_gen/test/run_suite.py \
+            --suite 1-gpu \
+            --partition-id ${{ matrix.part }} \
+            --total-partitions 2
+
+      - name: Collect diffusion performance metrics
+        if: always()
+        run: |
+          python3 scripts/ci/utils/diffusion/save_diffusion_metrics.py \
+            --gpu-config 1-gpu-h100 \
+            --run-id ${{ github.run_id }} \
+            --output python/diffusion-metrics-1gpu-partition-${{ matrix.part }}.json \
+            --results-json python/diffusion-results.json
+
+      - name: Upload diffusion metrics
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: diffusion-metrics-1gpu-partition-${{ matrix.part }}
+          path: python/diffusion-metrics-1gpu-partition-${{ matrix.part }}.json
+          retention-days: 90
+          if-no-files-found: ignore
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+        with:
+          artifact-suffix: ${{ matrix.part }}
+
+  nightly-test-multimodal-server-2-gpu:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-multimodal-server-2-gpu')
+    runs-on: 2-gpu-h100
+    strategy:
+      fail-fast: false
+      max-parallel: 5
+      matrix:
+        part: [0, 1]
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+          pip install slack_sdk
+
+      - name: Run diffusion server tests
+        env:
+          SGLANG_DIFFUSION_SLACK_TOKEN: ${{ secrets.SGLANG_DIFFUSION_SLACK_TOKEN }}
+          GITHUB_RUN_ID: ${{ github.run_id }}
+          GPU_CONFIG: "2-gpu-h100"
+
+        timeout-minutes: 90
+        run: |
+          cd python
+          python3 sglang/multimodal_gen/test/run_suite.py \
+            --suite 2-gpu \
+            --partition-id ${{ matrix.part }} \
+            --total-partitions 2
+
+      - name: Collect diffusion performance metrics
+        if: always()
+        run: |
+          python3 scripts/ci/utils/diffusion/save_diffusion_metrics.py \
+            --gpu-config 2-gpu-h100 \
+            --run-id ${{ github.run_id }} \
+            --output python/diffusion-metrics-2gpu-partition-${{ matrix.part }}.json \
+            --results-json python/diffusion-results.json
+
+      - name: Upload diffusion metrics
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: diffusion-metrics-2gpu-partition-${{ matrix.part }}
+          path: python/diffusion-metrics-2gpu-partition-${{ matrix.part }}.json
+          retention-days: 90
+          if-no-files-found: ignore
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+        with:
+          artifact-suffix: ${{ matrix.part }}
+
+  # B200 Performance tests - 4 GPU
+  nightly-test-perf-4-gpu-b200:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-perf-4-gpu-b200')
+    runs-on: 4-gpu-b200
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run test
+        timeout-minutes: 300
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite nightly-4-gpu-b200 --nightly --continue-on-error --timeout-per-file 12000
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+
+  # Specialized B200 tests - 8 GPU, for specific backends and configs
+  nightly-test-specialized-8-gpu-b200:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-perf-8-gpu-b200' || inputs.job_filter == 'nightly-test-specialized-8-gpu-b200')
+    runs-on: 8-gpu-b200
+    env:
+      RUNNER_LABELS: 8-gpu-b200
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run test
+        timeout-minutes: 120
+        env:
+          GPU_CONFIG: "8-gpu-b200"
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite nightly-8-gpu-b200 --nightly --continue-on-error --timeout-per-file 2400
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+
+  # Diffusion cross-framework comparison
+  nightly-test-diffusion-comparison:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-diffusion-comparison')
+    runs-on: 4-gpu-h100
+    timeout-minutes: 240
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+
+      - name: Run cross-framework comparison
+        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: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
+        run: |
+          python3 scripts/ci/utils/diffusion/publish_comparison_results.py \
+            --results comparison-results.json \
+            --dashboard dashboard.md \
+            --charts-dir comparison-charts
+
+      - name: Upload comparison artifacts
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: diffusion-comparison-${{ 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: always()
+
+  # Consolidate performance metrics from all jobs
+  consolidate-metrics:
+    if: github.repository == 'sgl-project/sglang' && always()
+    needs:
+      - nightly-test-general-8-gpu-h200
+      - nightly-test-general-8-gpu-b200
+      - nightly-test-multimodal-server-1-gpu
+      - nightly-test-multimodal-server-2-gpu
+    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-${{ github.run_id }}.json
+          retention-days: 90
+          if-no-files-found: warn
+
+  # Final check job
+  check-all-jobs:
+    if: github.repository == 'sgl-project/sglang' && always()
+    needs:
+      - nightly-test-general-1-gpu-h100
+      - nightly-test-general-4-gpu-h100
+      - nightly-test-general-8-gpu-h200
+      - nightly-test-general-8-gpu-h20
+      - nightly-test-general-8-gpu-b200
+      - nightly-test-text-accuracy-2-gpu-h100
+      - nightly-test-text-perf-2-gpu-h100
+      - nightly-test-vlm-accuracy-2-gpu-h100
+      - nightly-test-vlm-perf-2-gpu-h100
+      - nightly-test-multimodal-server-1-gpu
+      - nightly-test-multimodal-server-2-gpu
+      - nightly-test-perf-4-gpu-b200
+      - nightly-test-specialized-8-gpu-b200
+      - nightly-test-diffusion-comparison
+      - consolidate-metrics
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check if any job failed
+        run: |
+          if [[ "${{ 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"

third_party/sglang/.github/workflows/open-pr-copy-from-oss.yml

@@ -0,0 +1,28 @@
+name: Open A PR to Copy Code From OSS
+
+on:
+  workflow_dispatch:
+  # schedule:
+  #   - cron: '0 10 * * *'
+
+permissions:
+  contents: write
+
+jobs:
+  copy:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          ref: 'main'
+
+      - name: Install GitHub CLI (if not present)
+        run: |
+          bash scripts/code_sync/install_github_cli.sh
+
+      - name: Copy from OSS code
+        env:
+          GH_TOKEN: ${{ secrets.GH_PAT_FOR_OPEN_PR_TO_PRIVATE }}
+        run: |
+          python3 scripts/code_sync/copy_from_oss.py

third_party/sglang/.github/workflows/open-pr-copy-to-oss.yml

@@ -0,0 +1,31 @@
+name: Open A PR to Copy Diff To OSS
+
+on:
+  workflow_dispatch:
+    inputs:
+      commit_sha:
+        description: 'The commit SHA to copy. Defaults to LAST to copy the latest commit.'
+        required: false
+        default: 'LAST'
+
+permissions:
+  contents: write
+
+jobs:
+  copy:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Install GitHub CLI (if not present)
+        run: |
+          bash scripts/code_sync/install_github_cli.sh
+
+      - name: Copy to OSS code
+        env:
+          GH_TOKEN: ${{ secrets.GH_PAT_FOR_OPEN_PR_TO_OSS }}
+        run: |
+          python3 scripts/code_sync/copy_to_oss.py --commit ${{ github.event.inputs.commit_sha }}

third_party/sglang/.github/workflows/patch-docker-dev.yml

@@ -0,0 +1,115 @@
+name: Patch Docker Image
+
+on:
+  workflow_dispatch:
+    inputs:
+      pr_numbers:
+        description: "Comma-separated PR numbers to apply (e.g. 18962,19010)"
+        required: false
+        default: ""
+      image_tag:
+        description: "Base image tag to patch (e.g. dev-x86, dev-x86-cu13)"
+        required: true
+
+concurrency:
+  group: patch-docker-${{ inputs.image_tag }}
+  cancel-in-progress: true
+
+jobs:
+  patch:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: x64-docker-build-node
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Pull base image and extract commit
+        run: |
+          IMAGE="lmsysorg/sglang:${{ inputs.image_tag }}"
+          docker pull "${IMAGE}"
+          if BASE_SHA=$(docker run --rm "${IMAGE}" git -C /sgl-workspace/sglang rev-parse HEAD 2>/dev/null); then
+            echo "Image built from commit: ${BASE_SHA}"
+          else
+            BASE_SHA=""
+            echo "::warning::Image has no .git directory — cannot extract base commit"
+          fi
+          echo "BASE_SHA=${BASE_SHA}" >> "$GITHUB_ENV"
+
+      - name: Generate patches
+        run: |
+          git config --global --add safe.directory "$GITHUB_WORKSPACE"
+          git fetch origin main
+          mkdir -p /tmp/patch-ctx
+
+          if [ -n "${{ inputs.pr_numbers }}" ]; then
+            IFS=',' read -ra PRS <<< "${{ inputs.pr_numbers }}"
+            for pr in "${PRS[@]}"; do
+              pr=$(echo "${pr}" | xargs)
+              echo "Fetching PR #${pr}"
+              git fetch origin "pull/${pr}/head:pr-${pr}"
+              MERGE_BASE=$(git merge-base origin/main "pr-${pr}")
+              echo "  PR #${pr}: merge-base=${MERGE_BASE}"
+              git diff "${MERGE_BASE}..pr-${pr}" > "/tmp/patch-ctx/${pr}.patch"
+              echo "  PR #${pr}: $(wc -l < /tmp/patch-ctx/${pr}.patch) lines"
+            done
+          elif [ -n "${BASE_SHA}" ]; then
+            echo "Generating diff: image ${BASE_SHA} → latest main"
+            git fetch origin "${BASE_SHA}"
+            git diff "${BASE_SHA}..origin/main" > /tmp/patch-ctx/main.patch
+            echo "  main: $(wc -l < /tmp/patch-ctx/main.patch) lines"
+          else
+            echo "::error::No PR numbers specified and image has no .git — cannot generate diff against main"
+            exit 1
+          fi
+
+          TOTAL=$(cat /tmp/patch-ctx/*.patch | wc -l)
+          if [ "${TOTAL}" -eq 0 ]; then
+            echo "::warning::All patches are empty — image is already up to date"
+            echo "SKIP_BUILD=true" >> "$GITHUB_ENV"
+          fi
+
+      - name: Build patched image
+        if: env.SKIP_BUILD != 'true'
+        run: |
+          IMAGE="lmsysorg/sglang:${{ inputs.image_tag }}"
+
+          cat <<'DOCKERFILE' > /tmp/patch-ctx/Dockerfile
+          ARG BASE_IMAGE
+          FROM ${BASE_IMAGE}
+          COPY *.patch /tmp/patches/
+          RUN cd /sgl-workspace/sglang \
+              && for p in /tmp/patches/*.patch; do \
+                   if [ ! -s "${p}" ]; then \
+                     echo "Skipping ${p} (empty)"; \
+                   else \
+                     echo "Applying ${p}..." \
+                     && patch -p1 --fuzz=2 --no-backup-if-mismatch -f < "${p}" \
+                     || { echo "ERROR: Failed to apply ${p}"; exit 1; }; \
+                   fi; \
+                 done \
+              && rm -rf /tmp/patches
+          DOCKERFILE
+
+          docker build \
+            --no-cache \
+            --build-arg BASE_IMAGE="${IMAGE}" \
+            -t "${IMAGE}" \
+            /tmp/patch-ctx/
+
+      - name: Push patched image
+        if: env.SKIP_BUILD != 'true'
+        run: |
+          IMAGE="lmsysorg/sglang:${{ inputs.image_tag }}"
+          docker push "${IMAGE}"
+
+          echo "### Patched \`${IMAGE}\`" >> "$GITHUB_STEP_SUMMARY"
+          echo "- **Base commit:** \`${BASE_SHA:-unknown (no .git)}\`" >> "$GITHUB_STEP_SUMMARY"
+          echo "- **Source:** ${{ inputs.pr_numbers && format('PRs: {0}', inputs.pr_numbers) || 'latest main' }}" >> "$GITHUB_STEP_SUMMARY"

third_party/sglang/.github/workflows/pr-benchmark-rust.yml

@@ -0,0 +1,198 @@
+name: PR Benchmark (SMG Components)
+
+on:
+  push:
+    branches: [ main ]
+    paths:
+      - "sgl-model-gateway/**"
+  pull_request:
+    branches: [ main ]
+    paths:
+      - "sgl-model-gateway/**"
+  workflow_dispatch:
+
+concurrency:
+  group: pr-benchmark-rust-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  RUSTC_WRAPPER: sccache
+  SCCACHE_GHA_ENABLED: "true"
+
+permissions:
+  contents: read
+  pull-requests: write
+  issues: write
+
+jobs:
+  benchmark-compile-check:
+    name: Benchmark Compilation Check
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_gateway_dependencies.sh
+
+      - name: Configure sccache
+        uses: mozilla-actions/sccache-action@v0.0.9
+        with:
+          version: "v0.12.0"
+          disable_annotations: true
+
+      - name: Rust cache
+        uses: Swatinem/rust-cache@v2
+        with:
+          workspaces: sgl-model-gateway
+          shared-key: "rust-cache"
+          save-if: true
+          cache-all-crates: true
+          cache-on-failure: true
+
+      - name: Check benchmarks compile
+        run: |
+          source "$HOME/.cargo/env"
+          cd sgl-model-gateway/
+          cargo check --benches
+
+      - name: Show sccache stats
+        if: always()
+        run: sccache --show-stats
+
+  benchmark:
+    name: Benchmark - ${{ matrix.name }}
+    if: |
+      github.repository == 'sgl-project/sglang' &&
+      (github.event_name == 'push' ||
+       github.event_name == 'workflow_dispatch' ||
+       (contains(github.event.pull_request.labels.*.name, 'router-benchmark') &&
+        contains(github.event.pull_request.labels.*.name, 'run-ci')))
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - name: Request Processing
+            bench_name: request_processing
+            bench_args: "benchmark_summary --exact"
+            runner: ubuntu-latest
+            sccache_version: "v0.12.0"
+            artifact_name: request-processing-results
+            artifact_path: criterion/benchmark_summary/
+          - name: Manual Policy
+            bench_name: manual_policy_benchmark
+            bench_args: ""
+            runner: ubuntu-latest
+            sccache_version: "v0.12.0"
+            artifact_name: manual-policy-results
+            artifact_path: criterion/manual_policy*/
+    runs-on: ${{ matrix.runner }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 100
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_gateway_dependencies.sh
+
+      - name: Configure sccache
+        uses: mozilla-actions/sccache-action@v0.0.9
+        with:
+          version: ${{ matrix.sccache_version }}
+          disable_annotations: true
+
+      - name: Rust cache
+        uses: Swatinem/rust-cache@v2
+        with:
+          workspaces: sgl-model-gateway
+          shared-key: "rust-cache"
+          cache-all-crates: true
+          cache-on-failure: true
+          save-if: true
+
+      - name: Run benchmark
+        timeout-minutes: 30
+        run: |
+          source "$HOME/.cargo/env"
+          cd sgl-model-gateway/
+          if command -v sccache &> /dev/null; then
+            echo "Testing sccache availability..."
+            export RUSTC_WRAPPER=sccache
+            export SCCACHE_GHA_ENABLED="true"
+            if sccache --start-server 2>/dev/null && sccache --show-stats 2>/dev/null; then
+              echo "sccache is working, using it for compilation"
+            else
+              echo "sccache failed to start, falling back to regular cargo"
+              unset RUSTC_WRAPPER
+              unset SCCACHE_GHA_ENABLED
+            fi
+          else
+            echo "sccache not available, using regular cargo"
+          fi
+          cargo bench --bench ${{ matrix.bench_name }} -- ${{ matrix.bench_args }} 2>&1 | tee benchmark_output.txt
+
+      - name: Upload benchmark results
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: ${{ matrix.artifact_name }}-${{ github.sha }}
+          path: |
+            sgl-model-gateway/target/${{ matrix.artifact_path }}
+            sgl-model-gateway/benchmark_output.txt
+          retention-days: 30
+
+      - name: Show sccache stats
+        if: always()
+        run: sccache --show-stats
+
+  benchmark-summary:
+    name: Benchmark Summary
+    needs: [benchmark]
+    if: always() && (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request')
+    runs-on: ubuntu-latest
+    steps:
+      - name: Download all benchmark results
+        uses: actions/download-artifact@v4
+        with:
+          pattern: '*-results-${{ github.sha }}'
+          path: benchmark-results
+
+      - name: Generate summary
+        run: |
+          generate_section() {
+            local title="$1" dir_name="$2" lines="${3:-100}"
+            local dir="benchmark-results/${dir_name}-${{ github.sha }}"
+            echo "### $title" >> summary.md
+            if [ -d "$dir" ]; then
+              echo "✅ **Completed**" >> summary.md
+              if [ -f "$dir/benchmark_output.txt" ]; then
+                echo -e "\n<details>\n<summary>View Results</summary>\n\n\`\`\`" >> summary.md
+                tail -"$lines" "$dir/benchmark_output.txt" >> summary.md
+                echo -e "\`\`\`\n</details>" >> summary.md
+              fi
+            else
+              echo "❌ Failed or skipped" >> summary.md
+            fi
+            echo "" >> summary.md
+          }
+
+          echo "## 🚀 Benchmark Results Summary" > summary.md
+          echo "" >> summary.md
+
+          generate_section "Request Processing" "request-processing-results" 60
+          generate_section "Manual Policy (Sticky Sessions)" "manual-policy-results" 100
+
+          echo -e "---\n_Generated at $(date -u '+%Y-%m-%d %H:%M:%S UTC')_" >> summary.md
+
+          cat summary.md
+          cat summary.md >> $GITHUB_STEP_SUMMARY
+
+      - name: Upload summary
+        uses: actions/upload-artifact@v4
+        with:
+          name: benchmark-summary-${{ github.sha }}
+          path: summary.md
+          retention-days: 30

third_party/sglang/.github/workflows/pr-gate.yml

@@ -0,0 +1,254 @@
+on:
+  workflow_call:
+    inputs:
+      require-run-ci:
+        description: "Whether the PR must have the run-ci label"
+        type: boolean
+        default: true
+      cool-down-minutes:
+        description: "Cooldown period in minutes for low-permission users; 0 disables rate limiting"
+        type: number
+        default: 120
+
+jobs:
+  pr-gate:
+    # 1. for commits on main: no gating needed
+    # 2. for workflow_dispatch: this can only be triggered by users with write access
+    runs-on: ubuntu-latest
+    steps:
+      - name: Fetch latest PR info
+        if: github.event_name == 'pull_request'
+        id: pr
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const pr = await github.rest.pulls.get({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              pull_number: context.issue.number
+            });
+            core.setOutput("labels", JSON.stringify(pr.data.labels.map(l => l.name)));
+            core.setOutput("draft", pr.data.draft);
+            core.setOutput("user", pr.data.user.login);
+
+      - name: Log PR info
+        if: github.event_name == 'pull_request'
+        run: |
+          echo "===== PR Info ====="
+          echo "PR Event: ${{ github.event_name }}"
+          echo "PR Labels: ${{ steps.pr.outputs.labels }}"
+          echo "PR Draft: ${{ steps.pr.outputs.draft }}"
+          echo "PR User: ${{ steps.pr.outputs.user }}"
+          echo "Require run-ci: ${{ inputs.require-run-ci }}"
+          echo "Cool down minutes: ${{ inputs.cool-down-minutes }}"
+          echo "==================="
+
+      - name: Block draft PR
+        if: github.event_name == 'pull_request' && fromJson(steps.pr.outputs.draft)
+        run: |
+          echo "PR is draft. Blocking CI."
+          exit 1
+
+      - name: Require run-ci label (optional)
+        if:  github.event_name == 'pull_request' && inputs.require-run-ci == true
+        run: |
+          labels='${{ steps.pr.outputs.labels }}'
+          if [[ "${{ contains(fromJson(steps.pr.outputs.labels), 'run-ci') }}" == "false" ]]; then
+            echo "Missing required label 'run-ci'. See https://docs.sglang.io/developer_guide/contribution_guide.html#how-to-trigger-ci-tests for more details."
+            exit 1
+          fi
+
+      - name: Enforce rate limit for low-permission actors (optional)
+        if: github.event_name == 'pull_request' && inputs.cool-down-minutes > 0
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const DEFAULT_MINUTES = Number("${{ inputs.cool-down-minutes }}");
+            const owner = context.repo.owner;
+            const repo = context.repo.repo;
+            const eventName = context.eventName;
+            const curRun = await github.rest.actions.getWorkflowRun({
+              owner, repo, run_id: context.runId
+            });
+            let triggeringActor = curRun.data.triggering_actor?.login || context.actor;
+            if (triggeringActor === "github-actions[bot]") {
+              triggeringActor = `${{ steps.pr.outputs.user }}`;
+              core.info(
+                `triggering_actor is github-actions[bot]; substituting PR author '${triggeringActor}'.`
+              );
+            }
+
+            async function hasHighPermission(username) {
+              try {
+                const { data } = await github.rest.repos.getCollaboratorPermissionLevel({ owner, repo, username });
+                const perm = data.permission || 'none';
+                return perm === 'write' || perm === 'maintain' || perm === 'admin';
+              } catch (e) {
+                if (e.status === 404 || e.status === 403) return false;
+                throw e;
+              }
+            }
+
+            if (await hasHighPermission(triggeringActor)) {
+              core.info(`Triggering user '${triggeringActor}' has high permission. No rate limit applied.`);
+              return;
+            }
+
+            let effectiveCooldownMinutes = DEFAULT_MINUTES;
+            let perUserCooldownMinutes = null;
+
+            try {
+              const contentResp = await github.rest.repos.getContent({
+                owner,
+                repo,
+                path: ".github/CI_PERMISSIONS.json",
+                ref: "main",
+              });
+
+              if (!Array.isArray(contentResp.data) && contentResp.data && "content" in contentResp.data) {
+                const raw = Buffer.from(
+                  contentResp.data.content,
+                  contentResp.data.encoding || "base64"
+                ).toString();
+                const ciPermissions = JSON.parse(raw);
+
+                const userPerm = ciPermissions[triggeringActor];
+                if (userPerm && typeof userPerm.cooldown_interval_minutes === "number") {
+                  perUserCooldownMinutes = userPerm.cooldown_interval_minutes;
+                  core.info(
+                    `Per-user cooldown for '${triggeringActor}' from CI_PERMISSIONS.json: ${perUserCooldownMinutes} minutes.`
+                  );
+                } else {
+                  core.info(`No per-user cooldown found for '${triggeringActor}' in CI_PERMISSIONS.json.`);
+                }
+              } else {
+                core.info("CI_PERMISSIONS.json content response is not a file; skipping per-user cooldown.");
+              }
+            } catch (e) {
+              core.info(`CI_PERMISSIONS.json not found or unreadable: ${e.message}. Using default rate limit only.`);
+            }
+
+            if (perUserCooldownMinutes !== null) {
+              effectiveCooldownMinutes = Math.min(effectiveCooldownMinutes, perUserCooldownMinutes);
+            }
+
+            if (effectiveCooldownMinutes <= 0) {
+              core.info(
+                `Effective cooldown for '${triggeringActor}' is 0 minutes; no rate limit enforced for this user.`
+              );
+              return;
+            }
+
+            const cutoff = new Date(Date.now() - effectiveCooldownMinutes * 60 * 1000);
+            core.info(
+              `Checking for workflow runs since ${cutoff.toISOString()} (last ${effectiveCooldownMinutes} minutes) for event '${eventName}'.`
+            );
+
+            const { data } = await github.rest.actions.listWorkflowRuns({
+              owner,
+              repo,
+              workflow_id: 'pr-test.yml',
+              event: eventName,
+              per_page: 100,
+            });
+
+            const runs = data.workflow_runs || [];
+
+            // Rate Limiting Logic:
+            // We only count workflow runs that actually consumed CI resources (i.e., passed the gate).
+            // A run "passes the gate" if any jobs beyond the gate jobs (check-changes, pr-gate, call-gate)
+            // actually executed (not skipped/cancelled). This prevents scenarios where:
+            // - User has PR A with missing 'run-ci' label (fails at gate)
+            // - User opens PR B with 'run-ci' label
+            // - PR B should be able to run even though PR A triggered a run recently
+
+            // Helper function to check if a run passed the gate (i.e., actually consumed CI resources)
+            async function didRunPassGate(run) {
+              try {
+                // Note: Fetching up to 100 jobs (API maximum). If a workflow has >100 jobs,
+                // we may miss some, but this is unlikely in practice.
+                const { data: jobsData } = await github.rest.actions.listJobsForWorkflowRun({
+                  owner, repo, run_id: run.id, per_page: 100
+                });
+                const jobs = jobsData.jobs || [];
+
+                // If no jobs exist yet, the run hasn't started consuming resources
+                if (jobs.length === 0) {
+                  core.info(`Run ${run.id} has no jobs yet; not counting against rate limit.`);
+                  return false;
+                }
+
+                // Gate jobs that don't consume significant CI resources
+                const gateJobs = ['check-changes', 'pr-gate', 'call-gate', 'pr-test-finish'];
+                const jobsBeyondGate = jobs.filter(j => !gateJobs.some(g => j.name === g || j.name.startsWith(g + ' ')));
+
+                // A job "ran" if it reached a terminal conclusion state that indicates actual execution
+                const ranStates = ['success', 'failure', 'timed_out', 'action_required'];
+                const hasJobsThatRan = jobsBeyondGate.some(j => j.conclusion && ranStates.includes(j.conclusion));
+                return hasJobsThatRan;
+              } catch (e) {
+                core.warning(`Could not check jobs for run ${run.id}: ${e.message}`);
+
+                // If it's a rate limit error, count it conservatively to prevent abuse
+                if (e.status === 429) {
+                  core.warning(`Hit rate limit checking run ${run.id}; counting it to be safe.`);
+                  return true;
+                }
+
+                // For cancelled/skipped runs, they likely didn't consume resources
+                if (run.conclusion === 'cancelled' || run.conclusion === 'skipped') {
+                  return false;
+                }
+
+                // Default to counting it to prevent abuse
+                return true;
+              }
+            }
+
+            // Limit the number of runs we'll check in detail to avoid API rate limits
+            const MAX_RUNS_TO_CHECK = 5;
+            let runsChecked = 0;
+            let runsSkippedAtGate = 0;
+            let recentFound = null;
+
+            for (const run of runs) {
+              if (String(run.id) === String(context.runId)) continue;
+              if (new Date(run.created_at) < cutoff) continue;
+              const isUserRun = (run.actor?.login === triggeringActor) || (run.triggering_actor?.login === triggeringActor);
+              if (!isUserRun) continue;
+
+              runsChecked++;
+              core.info(`Checking run ${run.id} (created: ${run.created_at}, conclusion: ${run.conclusion})`);
+
+              // Safety limit: if we've checked too many runs, assume the next one passed to be conservative
+              if (runsChecked > MAX_RUNS_TO_CHECK) {
+                core.warning(`Checked ${MAX_RUNS_TO_CHECK} runs; assuming this one passed gate to avoid API limits.`);
+                recentFound = run;
+                break;
+              }
+
+              // Only count runs that actually passed the gate and consumed CI resources
+              if (await didRunPassGate(run)) {
+                recentFound = run;
+                core.info(`Found recent run ${run.id} that passed gate.`);
+                break;
+              } else {
+                runsSkippedAtGate++;
+                core.info(`Run ${run.id} failed at gate; not counting against rate limit.`);
+              }
+            }
+
+            core.info(`Rate limit check summary: checked ${runsChecked} runs, ${runsSkippedAtGate} failed at gate.`);
+
+            if (recentFound) {
+              core.setFailed(
+                `User '${triggeringActor}' already triggered '${context.workflow}' via '${eventName}' at ${recentFound.created_at}. ` +
+                `Please wait ${effectiveCooldownMinutes} minutes before triggering again.`
+              );
+            } else {
+              core.info(
+                `No recent runs detected for '${triggeringActor}' within the last ${effectiveCooldownMinutes} minutes; proceeding.`
+              );
+            }

third_party/sglang/.github/workflows/pr-test-jit-kernel.yml

@@ -0,0 +1,117 @@
+name: PR Test - JIT Kernel
+
+on:
+  workflow_call:
+    inputs:
+      jit_kernel:
+        required: true
+        type: string
+      pr_head_sha:
+        required: false
+        type: string
+        default: ''
+      git_ref:
+        required: false
+        type: string
+        default: ''
+      target_stage:
+        required: false
+        type: string
+        default: ''
+      test_parallel_dispatch:
+        required: false
+        type: string
+        default: 'false'
+      skip_stage_health_check:
+        required: false
+        type: boolean
+        default: false
+
+# Workflow-level env is NOT inherited from the caller in reusable workflows (verified by CI test).
+# The github context (including github.event_name) IS inherited from the caller.
+env:
+  SGLANG_IS_IN_CI: true
+  SGLANG_CUDA_COREDUMP: "1"
+  SGLANG_JIT_DEEPGEMM_FAST_WARMUP: true
+  SGLANG_PR_TEST_BYPASS_MAINTENANCE_ON_MAIN: ${{ github.ref == 'refs/heads/main' && 'true' || 'false' }}
+  SKIP_STAGE_HEALTH_CHECK: ${{ inputs.skip_stage_health_check == true && 'true' || 'false' }}
+
+jobs:
+  jit-kernel-unit-test:
+    if: |
+      github.event_name != 'schedule' &&
+      inputs.test_parallel_dispatch != 'true' &&
+      !inputs.target_stage
+    runs-on: 1-gpu-h100
+    timeout-minutes: 240
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
+
+      - uses: ./.github/actions/check-stage-health
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+
+      - name: Run test
+        timeout-minutes: 30
+        run: |
+          cd test/
+          python3 run_suite.py --hw cuda --suite stage-b-kernel-unit-1-gpu-large
+
+  jit-kernel-multigpu-unit-test:
+    if: |
+      github.event_name != 'schedule' &&
+      inputs.test_parallel_dispatch != 'true' &&
+      !inputs.target_stage
+    runs-on: 8-gpu-h200
+    timeout-minutes: 240
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+
+      - name: Run multi-GPU test
+        timeout-minutes: 45
+        run: |
+          cd test/
+          python3 run_suite.py --hw cuda --suite stage-b-kernel-unit-8-gpu-h200
+
+  jit-kernel-benchmark-test:
+    if: |
+      github.event_name != 'schedule' &&
+      inputs.test_parallel_dispatch != 'true' &&
+      !inputs.target_stage
+    runs-on: 1-gpu-h100
+    timeout-minutes: 240
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
+
+      - uses: ./.github/actions/check-stage-health
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+
+      - name: Run benchmark tests
+        timeout-minutes: 45
+        run: |
+          cd test/
+          python3 run_suite.py --hw cuda --suite stage-b-kernel-benchmark-1-gpu-large

third_party/sglang/.github/workflows/pr-test-multimodal-gen.yml

@@ -0,0 +1,245 @@
+name: PR Test - Multimodal Gen
+
+on:
+  workflow_call:
+    inputs:
+      multimodal_gen:
+        required: true
+        type: string
+      sgl_kernel:
+        required: true
+        type: string
+      b200_runner:
+        required: true
+        type: string
+      continue_on_error:
+        required: false
+        type: string
+        default: 'false'
+      pr_head_sha:
+        required: false
+        type: string
+        default: ''
+      git_ref:
+        required: false
+        type: string
+        default: ''
+      target_stage:
+        required: false
+        type: string
+        default: ''
+      test_parallel_dispatch:
+        required: false
+        type: string
+        default: 'false'
+      caller_needs_failure:
+        required: false
+        type: string
+        default: 'false'
+      skip_stage_health_check:
+        required: false
+        type: string
+        default: 'false'
+
+# Workflow-level env is NOT inherited from the caller in reusable workflows.
+# The github context (including github.event_name) IS inherited from the caller.
+env:
+  SGLANG_IS_IN_CI: true
+  SGLANG_CUDA_COREDUMP: "1"
+  SGLANG_PR_TEST_BYPASS_MAINTENANCE_ON_MAIN: ${{ github.ref == 'refs/heads/main' && 'true' || 'false' }}
+  SKIP_STAGE_HEALTH_CHECK: ${{ inputs.skip_stage_health_check == 'true' }}
+
+jobs:
+  multimodal-gen-test-1-gpu:
+    if: |
+      (inputs.target_stage == 'multimodal-gen-test-1-gpu') ||
+      (
+        !inputs.target_stage &&
+        ((github.event_name == 'schedule' || inputs.test_parallel_dispatch == 'true') || (inputs.caller_needs_failure != 'true' && !cancelled())) &&
+        inputs.multimodal_gen == 'true'
+      )
+    runs-on: 1-gpu-h100
+    timeout-minutes: 240
+    strategy:
+      fail-fast: false
+      matrix:
+        part: [0, 1]
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
+
+      - uses: ./.github/actions/check-stage-health
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Download artifacts
+        if: inputs.sgl_kernel == 'true'
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-python3.10-cuda12.9
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+      - name: Run diffusion server tests
+        timeout-minutes: 240
+        env:
+          RUNAI_STREAMER_MEMORY_LIMIT: 0
+          CONTINUE_ON_ERROR_FLAG: ${{ inputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
+        run: |
+          cd python
+          python3 sglang/multimodal_gen/test/run_suite.py \
+            --suite 1-gpu \
+            --partition-id ${{ matrix.part }} \
+            --total-partitions 2 \
+            $CONTINUE_ON_ERROR_FLAG
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+        with:
+          artifact-suffix: ${{ matrix.part }}
+
+  multimodal-gen-test-2-gpu:
+    if: |
+      (inputs.target_stage == 'multimodal-gen-test-2-gpu') ||
+      (
+        !inputs.target_stage &&
+        ((github.event_name == 'schedule' || inputs.test_parallel_dispatch == 'true') || (inputs.caller_needs_failure != 'true' && !cancelled())) &&
+        inputs.multimodal_gen == 'true'
+      )
+    runs-on: 2-gpu-h100
+    timeout-minutes: 240
+    strategy:
+      fail-fast: false
+      matrix:
+        part: [0, 1]
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
+
+      - uses: ./.github/actions/check-stage-health
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Download artifacts
+        if: inputs.sgl_kernel == 'true'
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-python3.10-cuda12.9
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+
+      - name: Run diffusion server tests
+        timeout-minutes: 240
+        env:
+          RUNAI_STREAMER_MEMORY_LIMIT: 0
+          CONTINUE_ON_ERROR_FLAG: ${{ inputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
+        run: |
+          cd python
+          python3 sglang/multimodal_gen/test/run_suite.py \
+            --suite 2-gpu \
+            --partition-id ${{ matrix.part }} \
+            --total-partitions 2 \
+            $CONTINUE_ON_ERROR_FLAG
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+        with:
+          artifact-suffix: ${{ matrix.part }}
+
+  multimodal-gen-test-1-b200:
+    if: |
+      (inputs.target_stage == 'multimodal-gen-test-1-b200') ||
+      (
+        !inputs.target_stage &&
+        ((github.event_name == 'schedule' || inputs.test_parallel_dispatch == 'true') || (inputs.caller_needs_failure != 'true' && !cancelled())) &&
+        inputs.multimodal_gen == 'true'
+      )
+    runs-on: ${{ inputs.b200_runner }}
+    timeout-minutes: 240
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
+
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Download artifacts
+        if: inputs.sgl_kernel == 'true'
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-python3.10-cuda12.9
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+
+      - name: Run diffusion server tests
+        timeout-minutes: 240
+        env:
+          RUNAI_STREAMER_MEMORY_LIMIT: 0
+          CONTINUE_ON_ERROR_FLAG: ${{ inputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
+        run: |
+          cd python
+          python3 sglang/multimodal_gen/test/run_suite.py \
+            --suite 1-gpu-b200 \
+            $CONTINUE_ON_ERROR_FLAG
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+
+  multimodal-gen-unit-test:
+    if: |
+      (inputs.target_stage == 'multimodal-gen-unit-test') ||
+      (
+        !inputs.target_stage &&
+        ((github.event_name == 'schedule' || inputs.test_parallel_dispatch == 'true') || (inputs.caller_needs_failure != 'true' && !cancelled())) &&
+        inputs.multimodal_gen == 'true'
+      )
+    runs-on: 1-gpu-h100
+    timeout-minutes: 120
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
+
+      - uses: ./.github/actions/check-stage-health
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Download artifacts
+        if: inputs.sgl_kernel == 'true'
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-python3.10-cuda12.9
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+
+      - name: Run diffusion unit tests
+        timeout-minutes: 60
+        run: |
+          cd python
+          python3 sglang/multimodal_gen/test/run_suite.py --suite unit

third_party/sglang/.github/workflows/pr-test-npu.yml

@@ -0,0 +1,453 @@
+name: PR Test (NPU)
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+  workflow_dispatch:
+  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: ''
+      run_all_tests:
+        description: "Run all tests (for releasing or testing purpose)"
+        required: false
+        type: boolean
+        default: false
+
+concurrency:
+  group: pr-test-npu-${{ inputs.ref || github.ref }}
+  cancel-in-progress: ${{ github.event_name != 'workflow_call' }}
+
+jobs:
+  # ==================== Check Changes ==================== #
+  check-changes:
+    runs-on: ubuntu-latest
+    outputs:
+      changes_exist: ${{ steps.filter.outputs.main_package == 'true' || steps.filter.outputs.multimodal_gen == 'true' || steps.run-mode.outputs.run_all_tests == 'true'}}
+      main_package: ${{ steps.filter.outputs.main_package == 'true' || steps.run-mode.outputs.run_all_tests == 'true' }}
+      multimodal_gen: ${{ steps.filter.outputs.multimodal_gen == 'true' || steps.run-mode.outputs.run_all_tests == 'true' }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Determine run mode
+        id: run-mode
+        run: |
+          # Run all tests for workflow_call (when ref input is provided)
+          # Note: github.event_name is inherited from caller, so we detect workflow_call by checking inputs.ref
+          if [[ "${{ inputs.run_all_tests }}" == "true" ]]; then
+            echo "run_all_tests=true" >> $GITHUB_OUTPUT
+            echo "Run mode: ALL TESTS (run_all_tests=${{ inputs.run_all_tests }})"
+          else
+            echo "run_all_tests=false" >> $GITHUB_OUTPUT
+            echo "Run mode: FILTERED (triggered by ${{ github.event_name }})"
+          fi
+
+      - name: Detect file changes
+        id: filter
+        uses: dorny/paths-filter@v3
+        if: steps.run-mode.outputs.run_all_tests != 'true'
+        with:
+          filters: |
+            main_package:
+              - "python/sglang/!(multimodal_gen)/**/!(*.md)"
+              - "python/pyproject_npu.toml"
+              - "scripts/ci/npu/npu_ci_install_dependency.sh"
+              - "test/srt/ascend/**"
+              - ".github/workflows/pr-test-npu.yml"
+            multimodal_gen:
+              - "python/sglang/multimodal_gen/**/*.!(md|ipynb)"
+              - "python/sglang/srt/**"
+              - "python/pyproject_npu.toml"
+              - "scripts/ci/npu/npu_ci_install_dependency.sh"
+              - ".github/workflows/pr-test-npu.yml"
+
+  # ==================== PR Gate ==================== #
+  pr-gate:
+    needs: check-changes
+    if: needs.check-changes.outputs.changes_exist == 'true'
+    uses: ./.github/workflows/pr-gate.yml
+    secrets: inherit
+
+  stage-b-test-1-npu-a2:
+    needs: [check-changes, pr-gate]
+    if: needs.check-changes.outputs.main_package == 'true'
+    runs-on: linux-aarch64-a2-1
+    strategy:
+      fail-fast: false
+      matrix:
+        part: [ 0, 1 ]
+    container:
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-910b-ubuntu22.04-py3.11
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Mark repository safe
+        run: |
+          git config --system --add safe.directory ${GITHUB_WORKSPACE}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          bash scripts/ci/npu/npu_ci_install_dependency.sh 910b
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Run test
+        timeout-minutes: 60
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          cd test
+          python3 run_suite.py --hw npu --suite stage-b-test-1-npu-a2 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
+
+  stage-b-test-2-npu-a2:
+    needs: [check-changes, pr-gate]
+    if: needs.check-changes.outputs.main_package == 'true'
+    runs-on: linux-aarch64-a2-2
+    strategy:
+      fail-fast: true
+      matrix:
+        part: [0, 1]
+    container:
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-910b-ubuntu22.04-py3.11
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Mark repository safe
+        run: |
+          git config --system --add safe.directory ${GITHUB_WORKSPACE}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          bash scripts/ci/npu/npu_ci_install_dependency.sh 910b
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Run test
+        timeout-minutes: 60
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          cd test
+          python3 run_suite.py --hw npu --suite stage-b-test-2-npu-a2 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
+
+  stage-b-test-4-npu-a3:
+    needs: [check-changes, pr-gate]
+    if: needs.check-changes.outputs.main_package == 'true'
+    runs-on: linux-aarch64-a3-4
+    container:
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Mark repository safe
+        run: |
+          git config --system --add safe.directory ${GITHUB_WORKSPACE}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          bash scripts/ci/npu/npu_ci_install_dependency.sh a3
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Run test
+        timeout-minutes: 60
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          cd test
+          python3 run_suite.py --hw npu --suite stage-b-test-4-npu-a3 --timeout-per-file 3600
+
+
+  stage-b-test-16-npu-a3:
+    needs: [check-changes, pr-gate]
+    if: needs.check-changes.outputs.main_package == 'true'
+    runs-on: linux-aarch64-a3-16
+    container:
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Mark repository safe
+        run: |
+          git config --system --add safe.directory ${GITHUB_WORKSPACE}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          bash scripts/ci/npu/npu_ci_install_dependency.sh a3
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Run test
+        timeout-minutes: 60
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          cd test
+          python3 run_suite.py --hw npu --suite stage-b-test-16-npu-a3 --timeout-per-file 3600
+
+  multimodal-gen-test-1-npu-a3:
+    needs: [check-changes, pr-gate]
+    if: needs.check-changes.outputs.multimodal_gen == 'true'
+    runs-on: linux-aarch64-a3-2
+    container:
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-a3-ubuntu22.04-py3.11
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Mark repository safe
+        run: |
+          git config --system --add safe.directory ${GITHUB_WORKSPACE}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          bash scripts/ci/npu/npu_ci_install_dependency.sh a3 diffusion
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Run test
+        timeout-minutes: 60
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
+          cd python
+          python3 sglang/multimodal_gen/test/run_suite.py --suite 1-npu
+
+  multimodal-gen-test-2-npu-a3:
+    needs: [check-changes, pr-gate]
+    if: needs.check-changes.outputs.multimodal_gen == 'true'
+    runs-on: linux-aarch64-a3-16
+    container:
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-a3-ubuntu22.04-py3.11
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Mark repository safe
+        run: |
+          git config --system --add safe.directory ${GITHUB_WORKSPACE}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          bash scripts/ci/npu/npu_ci_install_dependency.sh a3 diffusion
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Run test
+        timeout-minutes: 60
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
+          cd python
+          python3 sglang/multimodal_gen/test/run_suite.py --suite 2-npu
+
+  multimodal-gen-test-8-npu-a3:
+    needs: [check-changes, pr-gate]
+    if: needs.check-changes.outputs.multimodal_gen == 'true'
+    runs-on: linux-aarch64-a3-8
+    container:
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Mark repository safe
+        run: |
+          git config --system --add safe.directory ${GITHUB_WORKSPACE}
+
+      - name: Install dependencies
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+        run: |
+          # speed up by using infra cache services
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
+          pip config set global.index-url http://${CACHING_URL}/pypi/simple
+          pip config set global.trusted-host "${CACHING_URL}"
+
+          bash scripts/ci/npu/npu_ci_install_dependency.sh a3 diffusion
+          # copy required file from our daily cache
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+          # copy gsm8k dataset
+          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
+
+      - name: Run test
+        timeout-minutes: 60
+        env:
+          SGLANG_USE_MODELSCOPE: true
+          SGLANG_IS_IN_CI: true
+          HF_ENDPOINT: https://hf-mirror.com
+          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
+          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+          STREAMS_PER_DEVICE: 32
+        run: |
+          cd python
+          python3 sglang/multimodal_gen/test/run_suite.py --suite 8-npu
+
+  pr-test-npu-finish:
+    needs:
+      [
+        check-changes,
+
+        stage-b-test-1-npu-a2,
+        stage-b-test-2-npu-a2,
+        stage-b-test-4-npu-a3,
+        stage-b-test-16-npu-a3,
+
+        multimodal-gen-test-1-npu-a3,
+        multimodal-gen-test-2-npu-a3,
+        multimodal-gen-test-8-npu-a3,
+      ]
+    if: always()
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check all dependent job statuses
+        run: |
+          # Convert the 'needs' context to a JSON string
+          json_needs='${{ toJson(needs) }}'
+
+          # Get a list of all job names from the JSON keys
+          job_names=$(echo "$json_needs" | jq -r 'keys_unsorted[]')
+
+          for job in $job_names; do
+            # For each job, extract its result
+            result=$(echo "$json_needs" | jq -r --arg j "$job" '.[$j].result')
+
+            # Print the job name and its result
+            echo "$job: $result"
+
+            # Check for failure or cancellation and exit if found
+            if [[ "$result" == "failure" || "$result" == "cancelled" ]]; then
+              echo "The above jobs failed."
+              exit 1
+            fi
+          done
+          # If the loop completes, all jobs were successful
+          echo "All jobs completed successfully"
+          exit 0

third_party/sglang/.github/workflows/pr-test-rust.yml

@@ -0,0 +1,359 @@
+name: PR Test (SMG)
+
+on:
+  push:
+    branches: [ main ]
+    paths:
+      - "sgl-model-gateway/**"
+  pull_request:
+    branches: [ main ]
+    types: [opened, synchronize, reopened, labeled]
+    paths:
+      - "sgl-model-gateway/**"
+  workflow_dispatch:
+
+concurrency:
+  group: gateway-tests-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  RUSTC_WRAPPER: sccache
+  SCCACHE_GHA_ENABLED: "true"
+  SGLANG_IS_IN_CI: true
+
+jobs:
+  build-wheel:
+    if: |
+      github.event_name != 'pull_request' ||
+      (github.event.action != 'labeled' && contains(github.event.pull_request.labels.*.name, 'run-ci')) ||
+      (github.event.action == 'labeled' && github.event.label.name == 'run-ci')
+    runs-on: 4-gpu-a10
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install rust dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_gateway_dependencies.sh
+
+      - name: Configure sccache
+        uses: mozilla-actions/sccache-action@v0.0.9
+        with:
+          version: "v0.12.0"
+          disable_annotations: true
+
+      - name: Rust cache
+        uses: Swatinem/rust-cache@v2
+        with:
+          workspaces: sgl-model-gateway
+          shared-key: "rust-cache"
+          cache-all-crates: true
+          cache-on-failure: true
+          save-if: true
+
+      - name: Build python binding
+        run: |
+          source "$HOME/.cargo/env"
+          export RUSTC_WRAPPER=sccache
+          cd sgl-model-gateway/bindings/python
+          python3 -m pip install --upgrade pip maturin
+          maturin build --profile ci --features vendored-openssl --out dist
+
+      - name: List built wheel
+        run: ls -lh sgl-model-gateway/bindings/python/dist/
+
+      - name: Upload wheel artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: smg-wheel
+          path: sgl-model-gateway/bindings/python/dist/*.whl
+          retention-days: 1
+
+      - name: Test wheel install
+        run: |
+          pip install sgl-model-gateway/bindings/python/dist/*.whl
+          python3 -c "import sglang_router; print('Python package: OK')"
+          python3 -c "from sglang_router.sglang_router_rs import Router; print('Rust extension: OK')"
+          python3 -m sglang_router.launch_router --help > /dev/null && echo "Entry point: OK"
+
+  python-unit-tests:
+    needs: build-wheel
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          path: sglang-repo
+
+      - name: Move sgl-model-gateway folder to root
+        run: |
+          mv sglang-repo/sgl-model-gateway/* .
+          rm -rf sglang-repo
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.13"
+
+      - name: Download wheel artifact
+        uses: actions/download-artifact@v4
+        with:
+          name: smg-wheel
+          path: dist/
+
+      - name: Install wheel
+        run: pip install dist/*.whl
+
+      - name: Run Python unit tests
+        run: |
+          cd bindings/python
+          python3 -m pip install pytest pytest-cov pytest-xdist
+          pytest -q tests --cov=sglang_router --cov-config=.coveragerc --cov-report=term-missing --cov-fail-under=80
+
+  unit-tests:
+    if: |
+      github.event_name != 'pull_request' ||
+      (github.event.action != 'labeled' && contains(github.event.pull_request.labels.*.name, 'run-ci')) ||
+      (github.event.action == 'labeled' && github.event.label.name == 'run-ci')
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_gateway_dependencies.sh
+
+      - name: Configure sccache
+        uses: mozilla-actions/sccache-action@v0.0.9
+        with:
+          version: "v0.12.0"
+          disable_annotations: true
+
+      - name: Rust cache
+        uses: Swatinem/rust-cache@v2
+        with:
+          workspaces: sgl-model-gateway
+          shared-key: "rust-cache"
+          cache-all-crates: true
+          cache-on-failure: true
+          save-if: true
+
+      - name: Run lint
+        run: |
+          source "$HOME/.cargo/env"
+          cd sgl-model-gateway/
+          rustup component add clippy
+          cargo clippy --all-targets --all-features -- -D warnings
+
+      - name: Run fmt
+        run: |
+          source "$HOME/.cargo/env"
+          cd sgl-model-gateway/
+          rustup component add --toolchain nightly-x86_64-unknown-linux-gnu rustfmt
+          rustup toolchain install nightly --profile minimal
+          cargo +nightly fmt -- --check
+
+      - name: Generate vision golden fixtures
+        run: |
+          pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu
+
+          pip install transformers pillow numpy scipy
+          pip install transformers pillow numpy
+          cd sgl-model-gateway/
+          python scripts/generate_vision_golden.py
+
+      - name: Run Rust tests
+        timeout-minutes: 20
+        run: |
+          source "$HOME/.cargo/env"
+          cd sgl-model-gateway/
+          cargo test
+
+      - name: Show sccache stats
+        if: always()
+        run: sccache --show-stats
+
+  gateway-e2e:
+    name: ${{ matrix.name }}
+    needs: build-wheel
+    if: |
+      github.event_name != 'pull_request' ||
+      (github.event.action != 'labeled' && contains(github.event.pull_request.labels.*.name, 'run-ci')) ||
+      (github.event.action == 'labeled' && github.event.label.name == 'run-ci')
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - name: benchmarks
+            timeout: 32
+            test_dirs: "e2e_test/benchmarks"
+            extra_deps: "genai-bench==0.0.3"
+            env_vars: ""
+            reruns: ""
+            upload_benchmarks: true
+            parallel_opts: ""  # No parallel for benchmarks (performance measurement)
+          - name: responses
+            timeout: 45
+            test_dirs: "e2e_test/responses"
+            extra_deps: ""
+            env_vars: "SHOW_WORKER_LOGS=0 SHOW_ROUTER_LOGS=1"
+            reruns: "--reruns 2 --reruns-delay 5"
+            setup_oracle: true
+            setup_brave: true
+            parallel_opts: ""  # Cloud backend tests not compatible with parallel execution
+          - name: e2e
+            timeout: 45
+            test_dirs: "e2e_test/router e2e_test/embeddings"
+            extra_deps: "pytest-parallel py"  # py is required for pytest-parallel with newer pytest
+            env_vars: "SHOW_WORKER_LOGS=0 SHOW_ROUTER_LOGS=1"
+            reruns: "--reruns 2 --reruns-delay 5"
+            parallel_opts: "--workers 1 --tests-per-worker 4"  # Thread-based parallelism
+          - name: chat-completions
+            timeout: 45
+            test_dirs: "e2e_test/chat_completions"
+            extra_deps: ""
+            env_vars: "SHOW_WORKER_LOGS=0 SHOW_ROUTER_LOGS=1"
+            reruns: "--reruns 2 --reruns-delay 5"
+            parallel_opts: ""
+    runs-on: 4-gpu-a10
+    timeout-minutes: ${{ matrix.timeout }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install SGLang dependencies
+        run: |
+          sudo --preserve-env=PATH bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Setup Oracle Instant Client
+        if: matrix.setup_oracle
+        run: |
+          sudo apt-get install -y unzip
+          INSTANT_CLIENT_DIR="/home/ubuntu/instant-client"
+          INSTANT_CLIENT_ZIP="instantclient-basic-linux.x64-23.9.0.25.07.zip"
+
+          if [ ! -d "$INSTANT_CLIENT_DIR/instantclient_23_9" ]; then
+            echo "Downloading Oracle Instant Client..."
+            mkdir -p "$INSTANT_CLIENT_DIR"
+            cd "$INSTANT_CLIENT_DIR"
+            wget https://download.oracle.com/otn_software/linux/instantclient/2390000/$INSTANT_CLIENT_ZIP
+            unzip $INSTANT_CLIENT_ZIP
+            rm $INSTANT_CLIENT_ZIP
+          else
+            echo "Oracle Instant Client already exists, skipping download"
+          fi
+
+          echo "LD_LIBRARY_PATH=/home/ubuntu/instant-client/instantclient_23_9:\$LD_LIBRARY_PATH" >> $GITHUB_ENV
+
+      - name: Start Oracle Database
+        if: matrix.setup_oracle
+        run: |
+          docker run -d -p 1521:1521 -e ORACLE_PASSWORD=oracle --name oracle-db gvenzl/oracle-xe:21-slim
+          echo "Starting Oracle DB..."
+
+          # Export Oracle connection environment variables
+          echo "ATP_USER=system" >> $GITHUB_ENV
+          echo "ATP_PASSWORD=oracle" >> $GITHUB_ENV
+          echo "ATP_DSN=localhost:1521/XEPDB1" >> $GITHUB_ENV
+
+      - name: Start Brave MCP Server
+        if: matrix.setup_brave
+        run: |
+          docker run -d --rm \
+            -p 8001:8080 \
+            -e BRAVE_API_KEY \
+            --name brave-search-server \
+            shoofio/brave-search-mcp-sse:1.0.10
+          echo "Starting Brave MCP Server..."
+          sleep 2
+          curl -f --max-time 1 http://localhost:8001/sse > /dev/null 2>&1 && echo "Brave MCP Server is healthy!" || echo "Brave MCP Server responded"
+
+      - name: Download wheel artifact
+        uses: actions/download-artifact@v4
+        with:
+          name: smg-wheel
+          path: wheel/
+
+      - name: Install wheel
+        run: |
+          pip uninstall -y sglang-router || true
+          pip install wheel/*.whl
+
+      - name: Install e2e test dependencies
+        run: |
+          python3 -m pip install pytest pytest-rerunfailures httpx openai grpcio grpcio-health-checking numpy
+          if [ -n "${{ matrix.extra_deps }}" ]; then
+            python3 -m pip --no-cache-dir install --upgrade ${{ matrix.extra_deps }}
+          fi
+
+      - name: Run E2E tests
+        run: |
+          python3 python/sglang/cli/killall.py
+          cd sgl-model-gateway
+          ${{ matrix.env_vars }} ROUTER_LOCAL_MODEL_PATH="/home/ubuntu/models" pytest ${{ matrix.reruns }} ${{ matrix.parallel_opts }} ${{ matrix.test_dirs }} -s -vv -o log_cli=true --log-cli-level=INFO
+
+      - name: Upload benchmark results
+        if: matrix.upload_benchmarks && success()
+        uses: actions/upload-artifact@v4
+        with:
+          name: genai-bench-results-all-policies
+          path: sgl-model-gateway/benchmark_**/
+
+      - name: Cleanup Brave MCP Server
+        if: always() && matrix.setup_brave
+        run: |
+          docker stop brave-search-server || true
+          docker rm brave-search-server || true
+
+      - name: Cleanup Oracle Database
+        if: always() && matrix.setup_oracle
+        run: |
+          docker stop oracle-db || true
+          docker rm oracle-db || true
+
+  docker-build-test:
+    if: |
+      github.event_name != 'pull_request' ||
+      (github.event.action != 'labeled' && contains(github.event.pull_request.labels.*.name, 'run-ci')) ||
+      (github.event.action == 'labeled' && github.event.label.name == 'run-ci')
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build Docker image (no push)
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: docker/gateway.Dockerfile
+          push: false
+          tags: sgl-model-gateway:test
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+  finish:
+    needs: [build-wheel, python-unit-tests, unit-tests, gateway-e2e, docker-build-test]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Finish
+        run: echo "This is an empty step to ensure that all jobs are completed."
+
+  summarize-benchmarks:
+    needs: gateway-e2e
+    runs-on: ubuntu-latest
+    if: success()
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Download benchmark results
+      uses: actions/download-artifact@v4
+      with:
+        name: genai-bench-results-all-policies
+
+    - name: Create benchmark summary
+      run: python3 sgl-model-gateway/e2e_test/benchmarks/summarize.py .

third_party/sglang/.github/workflows/pr-test-sgl-kernel.yml

@@ -0,0 +1,214 @@
+name: PR Test - SGL Kernel
+
+on:
+  workflow_call:
+    inputs:
+      sgl_kernel:
+        required: true
+        type: string
+      b200_runner:
+        required: true
+        type: string
+      pr_head_sha:
+        required: false
+        type: string
+        default: ''
+      git_ref:
+        required: false
+        type: string
+        default: ''
+      skip_stage_health_check:
+        required: false
+        type: boolean
+        default: false
+
+# Workflow-level env is NOT inherited from the caller in reusable workflows.
+# The github context (including github.event_name) IS inherited from the caller.
+env:
+  SGLANG_IS_IN_CI: true
+  SGLANG_CUDA_COREDUMP: "1"
+  SGLANG_PR_TEST_BYPASS_MAINTENANCE_ON_MAIN: ${{ github.ref == 'refs/heads/main' && 'true' || 'false' }}
+  SKIP_STAGE_HEALTH_CHECK: ${{ inputs.skip_stage_health_check == true && 'true' || 'false' }}
+
+jobs:
+  sgl-kernel-unit-test:
+    runs-on: 1-gpu-h100
+    timeout-minutes: 240
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
+
+      - uses: ./.github/actions/check-stage-health
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Cleanup
+        run: |
+          ls -alh sgl-kernel/dist || true
+          rm -rf sgl-kernel/dist/* || true
+
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-python3.10-cuda12.9
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+
+      - name: Run test
+        timeout-minutes: 30
+        run: |
+          cd sgl-kernel
+          pytest tests/
+
+  sgl-kernel-mla-test:
+    runs-on: 1-gpu-h100
+    timeout-minutes: 240
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
+
+      - uses: ./.github/actions/check-stage-health
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Cleanup
+        run: |
+          ls -alh sgl-kernel/dist || true
+          rm -rf sgl-kernel/dist/* || true
+
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-python3.10-cuda12.9
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run test
+        timeout-minutes: 30
+        run: |
+          cd test/registered/mla
+          python3 test_mla_deepseek_v3.py
+
+  sgl-kernel-benchmark-test:
+    runs-on: 1-gpu-h100
+    timeout-minutes: 240
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
+
+      - uses: ./.github/actions/check-stage-health
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Cleanup
+        run: |
+          ls -alh sgl-kernel/dist || true
+          rm -rf sgl-kernel/dist/* || true
+
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-python3.10-cuda12.9
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run benchmark tests
+        timeout-minutes: 45
+        run: |
+          cd sgl-kernel/benchmark
+          echo "Running sgl-kernel benchmark tests in CI mode..."
+
+          echo "CI environment variable: $CI"
+          echo "GITHUB_ACTIONS environment variable: $GITHUB_ACTIONS"
+
+          for bench_file in bench_*.py; do
+            echo "Testing $bench_file..."
+            timeout 60 python3 "$bench_file" || echo "Warning: $bench_file timed out or failed, continuing..."
+            echo "Completed $bench_file"
+            echo "---"
+          done
+
+          echo "All benchmark tests completed!"
+
+  sgl-kernel-b200-test:
+    runs-on: ${{ inputs.b200_runner }}
+    timeout-minutes: 240
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
+
+      - uses: ./.github/actions/check-stage-health
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Cleanup
+        run: |
+          ls -alh sgl-kernel/dist || true
+          rm -rf sgl-kernel/dist/* || true
+
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-python3.10-cuda12.9
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+
+      - name: Run sgl-kernel unit tests on B200
+        timeout-minutes: 30
+        run: |
+          cd sgl-kernel
+          pytest tests/
+
+  # Adding a single CUDA13 smoke test to verify that the kernel builds and runs
+  # TODO: Add back this test when it can pass on CI
+  # cuda13-kernel-smoke-test:
+  #   if: inputs.sgl_kernel == 'true'
+  #   runs-on: x64-cu13-kernel-tests
+  #   steps:
+  #     - uses: actions/checkout@v4
+
+  #     - name: Cleanup
+  #       run: |
+  #         ls -alh sgl-kernel/dist || true
+  #         rm -rf sgl-kernel/dist/* || true
+
+  #     - name: Download CUDA 13.0 artifacts
+  #       uses: actions/download-artifact@v4
+  #       with:
+  #         path: sgl-kernel/dist/
+  #         merge-multiple: true
+  #         pattern: wheel-python3.10-cuda13.0
+
+  #     - name: Install dependencies
+  #       run: |
+  #         CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh
+
+  #     - name: Run kernel unit tests
+  #       timeout-minutes: 30
+  #       run: |
+  #         cd sgl-kernel
+  #         pytest tests/

third_party/sglang/.github/workflows/pr-test-xeon.yml

@@ -0,0 +1,131 @@
+name: PR Test (Xeon)
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+  workflow_dispatch:
+  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: ''
+      run_all_tests:
+        description: "Run all tests (for releasing or testing purpose)"
+        required: false
+        type: boolean
+        default: false
+
+concurrency:
+  group: pr-test-xeon-${{ inputs.ref || github.ref }}
+  cancel-in-progress: false
+
+jobs:
+  # ==================== Check Changes ==================== #
+  check-changes:
+    runs-on: ubuntu-latest
+    outputs:
+      main_package: ${{ steps.filter.outputs.main_package || steps.run-mode.outputs.run_all_tests}}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Determine run mode
+        id: run-mode
+        run: |
+          # Run all tests for workflow_call (when ref input is provided)
+          # Note: github.event_name is inherited from caller, so we detect workflow_call by checking inputs.ref
+          if [[ "${{ inputs.run_all_tests }}" == "true" ]]; then
+            echo "run_all_tests=true" >> $GITHUB_OUTPUT
+            echo "Run mode: ALL TESTS (run_all_tests=${{ inputs.run_all_tests }})"
+          else
+            echo "run_all_tests=false" >> $GITHUB_OUTPUT
+            echo "Run mode: FILTERED (triggered by ${{ github.event_name }})"
+          fi
+
+      - name: Detect file changes
+        id: filter
+        uses: dorny/paths-filter@v3
+        if: steps.run-mode.outputs.run_all_tests != 'true'
+        with:
+          filters: |
+            main_package:
+              - "python/sglang/!(multimodal_gen)/**/!(*.md)"
+              - "python/pyproject_cpu.toml"
+              - "test/**/!(*.md)"
+              - "sgl-kernel/**/*.!(md|txt)"
+              - ".github/workflows/pr-test-xeon.yml"
+              - "docker/xeon.Dockerfile"
+
+  # ==================== PR Gate ==================== #
+  pr-gate:
+    needs: check-changes
+    if: needs.check-changes.outputs.main_package == 'true'
+    uses: ./.github/workflows/pr-gate.yml
+    secrets: inherit
+
+  build-test:
+    needs: [check-changes, pr-gate]
+    if: needs.check-changes.outputs.main_package == 'true'
+    runs-on: xeon-gnr
+    env:
+      HF_HOME: /home/sdp/.cache/huggingface
+    strategy:
+      matrix:
+        build_type: ['all']
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Build and Push
+        run: |
+          version=$(cat python/sglang/version.py | cut -d'"' -f2)
+          tag=v${version}-xeon
+          PR_REPO=${{ github.event.pull_request.head.repo.clone_url }}
+          PR_HEAD_REF=${{ github.head_ref }}
+
+          docker build \
+            ${PR_REPO:+--build-arg SGLANG_REPO=$PR_REPO} \
+            ${PR_HEAD_REF:+--build-arg VER_SGLANG=$PR_HEAD_REF} \
+            . -f docker/xeon.Dockerfile  -t sglang_xeon --no-cache
+
+      - name: Run container
+        run: |
+          docker run -dt \
+            -v ${{ github.workspace }}:/sglang-checkout/ --ipc=host \
+            -v ${HF_HOME}:/root/.cache/huggingface \
+            --name ci_sglang_xeon \
+            sglang_xeon
+
+      - name: Check AMX support
+        id: check_amx
+        timeout-minutes: 5
+        run: |
+          docker exec -w /sglang-checkout/ ci_sglang_xeon \
+            bash -c "source /opt/.venv/bin/activate && python3 -c 'import torch; import sgl_kernel; assert torch._C._cpu._is_amx_tile_supported(); assert hasattr(torch.ops.sgl_kernel, \"convert_weight_packed\"); '"
+
+      - name: Run unit tests
+        timeout-minutes: 36
+        run: |
+          docker exec -w /sglang-checkout/ ci_sglang_xeon \
+            bash -c "source /opt/.venv/bin/activate && cd ./test/srt && python3 run_suite.py --suite per-commit-cpu --timeout-per-file 1500"
+
+      - name: Change permission
+        timeout-minutes: 2
+        run: |
+          docker exec -u root ci_sglang_xeon bash -c "
+            rm -rf /tmp/ci-home  &&
+            chown -R  $(id -u):$(id -g) /sglang-checkout/ 2>/dev/null || true
+          "
+
+      - name: Cleanup container
+        if: always()
+        run: |
+          docker rm -f ci_sglang_xeon || true

third_party/sglang/.github/workflows/pr-test-xpu.yml

@@ -0,0 +1,143 @@
+name: PR Test (XPU)
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+  workflow_dispatch:
+  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: ''
+      run_all_tests:
+        description: "Run all tests (for releasing or testing purpose)"
+        required: false
+        type: boolean
+        default: false
+
+concurrency:
+  group: pr-test-xpu-${{ inputs.ref || github.ref }}
+  cancel-in-progress: ${{ github.event_name != 'workflow_call' }}
+
+jobs:
+  # ==================== Check Changes ==================== #
+  check-changes:
+    runs-on: ubuntu-latest
+    outputs:
+      main_package: ${{ steps.filter.outputs.main_package || steps.run-mode.outputs.run_all_tests }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Determine run mode
+        id: run-mode
+        run: |
+          # Run all tests for workflow_call (when ref input is provided)
+          # Note: github.event_name is inherited from caller, so we detect workflow_call by checking inputs.ref
+          if [[ "${{ inputs.run_all_tests }}" == "true" ]]; then
+            echo "run_all_tests=true" >> $GITHUB_OUTPUT
+            echo "Run mode: ALL TESTS (run_all_tests=${{ inputs.run_all_tests }})"
+          else
+            echo "run_all_tests=false" >> $GITHUB_OUTPUT
+            echo "Run mode: FILTERED (triggered by ${{ github.event_name }})"
+          fi
+      - name: Detect file changes
+        id: filter
+        uses: dorny/paths-filter@v3
+        if: steps.run-mode.outputs.run_all_tests != 'true'
+        with:
+          filters: |
+            main_package:
+              - "python/sglang/!(multimodal_gen)/**/!(*.md)"
+              - "python/pyproject_xpu.toml"
+              - "test/**/!(*.md)"
+              - "sgl-kernel/**/*.!(md|txt)"
+              - ".github/workflows/pr-test-xpu.yml"
+              - "docker/xpu.Dockerfile"
+
+  # ==================== PR Gate ==================== #
+  pr-gate:
+    needs: check-changes
+    if: needs.check-changes.outputs.main_package == 'true'
+    uses: ./.github/workflows/pr-gate.yml
+    secrets: inherit
+
+  build-and-test:
+    needs: [check-changes, pr-gate]
+    if: needs.check-changes.outputs.main_package == 'true'
+    runs-on: intel-bmg
+    env:
+      HF_HOME: /home/sdp/.cache/huggingface
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build Docker image
+        run: |
+          PR_REPO=${{ github.event.pull_request.head.repo.clone_url }}
+          PR_HEAD_REF=${{ github.head_ref }}
+          docker build \
+            ${PR_REPO:+--build-arg SG_LANG_REPO=$PR_REPO} \
+            ${PR_HEAD_REF:+--build-arg SG_LANG_BRANCH=$PR_HEAD_REF} \
+            --no-cache --progress=plain -f docker/xpu.Dockerfile -t xpu_sglang_main:bmg .
+
+      - name: Run container
+        id: start_container
+        run: |
+          container_id=$(docker run -dt \
+            --group-add 992 \
+            --group-add $(getent group video | cut -d: -f3) \
+            -v ${HF_HOME}:/root/.cache/huggingface \
+            --device /dev/dri \
+            -e HF_TOKEN="$(cat ~/huggingface_token.txt)" \
+            xpu_sglang_main:bmg)
+          echo "Started container: $container_id"
+          echo "container_id=$container_id" >> "$GITHUB_OUTPUT"
+
+      - name: Install Dependency
+        timeout-minutes: 20
+        run: |
+          cid="${{ steps.start_container.outputs.container_id }}"
+          docker exec "$cid" /home/sdp/miniforge3/envs/py3.10/bin/python3 -m pip install --upgrade pip
+          docker exec "$cid" /home/sdp/miniforge3/envs/py3.10/bin/python3 -m pip install pytest expecttest ray huggingface_hub
+          docker exec "$cid" /home/sdp/miniforge3/envs/py3.10/bin/python3 -m pip uninstall -y flashinfer-python
+          docker exec "$cid" /bin/bash -c '/home/sdp/miniforge3/envs/py3.10/bin/hf auth login --token ${HF_TOKEN} '
+
+
+      - name: Run E2E Bfloat16 tests
+        timeout-minutes: 20
+        run: |
+          cid="${{ steps.start_container.outputs.container_id }}"
+          docker exec "$cid" bash -c "source /home/sdp/miniforge3/bin/activate && conda activate py3.10 && cd /home/sdp/sglang/test/srt && python3 run_suite.py --suite per-commit-xpu"
+      - name: Cleanup container
+        if: always()
+        run: |
+          cid="${{ steps.start_container.outputs.container_id }}"
+          docker rm -f "$cid" || true
+
+  finish:
+    if: always()
+    needs: [build-and-test, pr-gate]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check job status
+        run: |
+          result="${{ needs.build-and-test.result }}"
+          if [ "$result" != "success" ] && [ "$result" != "skipped" ]; then
+            echo "Job failed with result: $result"
+            exit 1
+          fi
+          echo "All jobs completed successfully (result: $result)"
+          exit 0

third_party/sglang/.github/workflows/release-branch-cut.yml

@@ -0,0 +1,215 @@
+name: Release Branch Cut
+
+on:
+  workflow_dispatch:
+    inputs:
+      branch_name:
+        description: 'Branch name to create (e.g., release/v0.5.7)'
+        required: true
+        type: string
+      commit_sha:
+        description: 'Commit SHA from main to cut the release branch from (defaults to latest main)'
+        required: false
+        type: string
+        default: ''
+
+permissions:
+  actions: write
+  contents: write
+  issues: read
+  pull-requests: read
+
+jobs:
+  cut-release-branch:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: ubuntu-latest
+    environment: 'prod'
+    outputs:
+      branch_name: ${{ steps.set_output.outputs.branch_name }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          ref: main
+          fetch-depth: 0
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Validate branch name
+        run: |
+          BRANCH_NAME="${{ github.event.inputs.branch_name }}"
+
+          if [ -z "$BRANCH_NAME" ]; then
+            echo "::error::Branch name is required"
+            exit 1
+          fi
+
+          # Validate branch name format (should start with release/)
+          if [[ ! "$BRANCH_NAME" =~ ^release/ ]]; then
+            echo "::warning::Branch name '$BRANCH_NAME' does not follow convention 'release/vX.Y.Z'"
+          fi
+
+          echo "Branch name: $BRANCH_NAME"
+
+      - name: Validate commit SHA
+        id: validate
+        run: |
+          COMMIT_SHA="${{ github.event.inputs.commit_sha }}"
+
+          # If no commit SHA provided, use latest main
+          if [ -z "$COMMIT_SHA" ]; then
+            COMMIT_SHA=$(git rev-parse HEAD)
+            echo "No commit SHA provided, using latest main: $COMMIT_SHA"
+          fi
+
+          # Verify the commit exists and is on main
+          if ! git cat-file -t "$COMMIT_SHA" > /dev/null 2>&1; then
+            echo "::error::Commit SHA '$COMMIT_SHA' does not exist"
+            exit 1
+          fi
+
+          # Check if commit is an ancestor of main (i.e., is on main branch)
+          if ! git merge-base --is-ancestor "$COMMIT_SHA" main; then
+            echo "::error::Commit SHA '$COMMIT_SHA' is not on the main branch"
+            exit 1
+          fi
+
+          echo "COMMIT_SHA=$COMMIT_SHA" >> $GITHUB_OUTPUT
+          echo "Validated commit SHA: $COMMIT_SHA"
+
+      - name: Check if branch already exists
+        run: |
+          BRANCH_NAME="${{ github.event.inputs.branch_name }}"
+
+          if git ls-remote --heads origin "$BRANCH_NAME" | grep -q "$BRANCH_NAME"; then
+            echo "::error::Branch '$BRANCH_NAME' already exists"
+            exit 1
+          fi
+
+          echo "Branch '$BRANCH_NAME' does not exist, proceeding with creation"
+
+      - name: Create release branch
+        id: set_output
+        run: |
+          COMMIT_SHA="${{ steps.validate.outputs.COMMIT_SHA }}"
+          BRANCH_NAME="${{ github.event.inputs.branch_name }}"
+
+          git config user.name "sglang-bot"
+          git config user.email "sglang-bot@users.noreply.github.com"
+
+          # Create branch from the specified commit
+          git checkout -b "$BRANCH_NAME" "$COMMIT_SHA"
+
+          echo "branch_name=$BRANCH_NAME" >> $GITHUB_OUTPUT
+          echo "Successfully created branch '$BRANCH_NAME' from commit '$COMMIT_SHA'"
+
+      - name: Update version references in documentation
+        run: |
+          BRANCH_NAME="${{ github.event.inputs.branch_name }}"
+          # Extract version from branch name (e.g., release/v0.5.8 -> v0.5.8)
+          VERSION=$(echo "$BRANCH_NAME" | sed 's/release\///')
+
+          # Update git clone version references in docs
+          sed -i "s/git clone -b v[0-9]\+\.[0-9]\+\.[0-9]\+\.\?post\?[0-9]*/git clone -b $VERSION/" docs/get_started/install.md
+          sed -i "s/git clone -b v[0-9]\+\.[0-9]\+\.[0-9]\+\.\?post\?[0-9]*/git clone -b $VERSION/" docs/platforms/amd_gpu.md
+
+          # Check if any changes were made
+          if git diff --quiet; then
+            echo "No version references needed updating"
+          else
+            git add docs/get_started/install.md docs/platforms/amd_gpu.md
+            git commit -m "docs: update version references to $VERSION"
+            echo "Updated version references to $VERSION"
+          fi
+
+      - name: Push release branch
+        run: |
+          BRANCH_NAME="${{ steps.set_output.outputs.branch_name }}"
+          git push origin "$BRANCH_NAME"
+          echo "Successfully pushed branch '$BRANCH_NAME'"
+
+      - name: Summary
+        run: |
+          COMMIT_SHA="${{ steps.validate.outputs.COMMIT_SHA }}"
+          BRANCH_NAME="${{ github.event.inputs.branch_name }}"
+
+          echo "## Release Branch Cut Summary" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "| Property | Value |" >> $GITHUB_STEP_SUMMARY
+          echo "|----------|-------|" >> $GITHUB_STEP_SUMMARY
+          echo "| Branch | \`$BRANCH_NAME\` |" >> $GITHUB_STEP_SUMMARY
+          echo "| Commit | \`$COMMIT_SHA\` |" >> $GITHUB_STEP_SUMMARY
+          echo "| Triggered by | @${{ github.actor }} |" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### Next Steps" >> $GITHUB_STEP_SUMMARY
+          echo "1. Tests are automatically triggered on the release branch" >> $GITHUB_STEP_SUMMARY
+          echo "2. Apply any hotfixes if needed" >> $GITHUB_STEP_SUMMARY
+          echo "3. Create a tag to trigger release: \`gh workflow run release-tag.yml -f version=X.Y.Z -f ref=$BRANCH_NAME\`" >> $GITHUB_STEP_SUMMARY
+
+  run-pr-tests-nvidia:
+    needs: cut-release-branch
+    uses: ./.github/workflows/pr-test.yml
+    with:
+      git_ref: ${{ needs.cut-release-branch.outputs.branch_name }}
+      run_all_tests: true
+      skip_stage_health_check: true
+    secrets: inherit
+
+  run-pr-tests-amd:
+    needs: cut-release-branch
+    uses: ./.github/workflows/pr-test-amd.yml
+    with:
+      ref: ${{ needs.cut-release-branch.outputs.branch_name }}
+      run_all_tests: true
+    secrets: inherit
+
+  run-pr-test-npu:
+    needs: cut-release-branch
+    uses: ./.github/workflows/pr-test-npu.yml
+    with:
+      ref: ${{ needs.cut-release-branch.outputs.branch_name }}
+      run_all_tests: true
+    secrets: inherit
+
+  run-pr-tests-xeon:
+    needs: cut-release-branch
+    uses: ./.github/workflows/pr-test-xeon.yml
+    with:
+      ref: ${{ needs.cut-release-branch.outputs.branch_name }}
+      run_all_tests: true
+    secrets: inherit
+
+  run-pr-tests-xpu:
+    needs: cut-release-branch
+    uses: ./.github/workflows/pr-test-xpu.yml
+    with:
+      ref: ${{ needs.cut-release-branch.outputs.branch_name }}
+      run_all_tests: true
+    secrets: inherit
+
+  run-nightly-tests-nvidia:
+    needs: cut-release-branch
+    uses: ./.github/workflows/nightly-test-nvidia.yml
+    with:
+      ref: ${{ needs.cut-release-branch.outputs.branch_name }}
+    secrets: inherit
+
+  run-nightly-tests-amd:
+    needs: cut-release-branch
+    uses: ./.github/workflows/nightly-test-amd.yml
+    with:
+      ref: ${{ needs.cut-release-branch.outputs.branch_name }}
+    secrets: inherit
+
+  run-nightly-tests-npu:
+    needs: cut-release-branch
+    uses: ./.github/workflows/nightly-test-npu.yml
+    with:
+      ref: ${{ needs.cut-release-branch.outputs.branch_name }}
+    secrets: inherit
+
+  run-nightly-tests-intel:
+    needs: cut-release-branch
+    uses: ./.github/workflows/nightly-test-intel.yml
+    with:
+      ref: ${{ needs.cut-release-branch.outputs.branch_name }}
+    secrets: inherit

third_party/sglang/.github/workflows/release-docker-amd-nightly.yml

@@ -0,0 +1,182 @@
+name: Release Docker Images Nightly (AMD)
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: '0 12 * * *'
+
+concurrency:
+  # A PR number if a pull request and otherwise the commit hash. This cancels
+  # queued and in-progress runs for the same PR (presubmit) or commit
+  # (postsubmit). The workflow name is prepended to avoid conflicts between
+  # different workflows.
+  group: ${{ github.workflow }}-${{ github.event.number || github.sha }}
+  cancel-in-progress: true
+
+jobs:
+  publish:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: amd-docker-scale
+    environment: 'prod'
+    strategy:
+      fail-fast: false
+      matrix:
+        gpu_arch: ['gfx942', 'gfx950']
+        build_type: ['all']
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0  # Required for git describe to find tags
+
+      - name: "Set Date"
+        run: |
+          echo "DATE=$(date +%Y%m%d)" >> $GITHUB_ENV
+
+      - name: Get version from latest tag
+        id: version
+        run: |
+          # Get the latest version tag sorted by version number (e.g., v0.5.7 -> 0.5.7)
+          VERSION=$(git tag -l 'v[0-9]*' --sort=-v:refname | head -1 | sed 's/^v//')
+
+          if [ -z "$VERSION" ]; then
+            echo "::error::Could not determine version from git tags"
+            exit 1
+          fi
+
+          # Get short commit hash of current HEAD
+          COMMIT_HASH=$(git rev-parse --short HEAD)
+
+          # Compose pretend version for setuptools_scm: e.g., 0.5.8.dev20260129+g1a2b3c4
+          PRETEND_VERSION="${VERSION}.dev${{ env.DATE }}+g${COMMIT_HASH}"
+
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+          echo "pretend_version=${PRETEND_VERSION}" >> $GITHUB_OUTPUT
+          echo "Detected version: ${VERSION}"
+          echo "Pretend version for pip: ${PRETEND_VERSION}"
+
+      - name: Login to Docker Hub (AMD)
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_AMD_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_AMD_TOKEN }}
+
+      - name: Build and Push to rocm/sgl-dev
+        run: |
+          version=${{ steps.version.outputs.version }}
+          pretend_version=${{ steps.version.outputs.pretend_version }}
+          echo "Version: ${version}"
+          echo "Pretend version: ${pretend_version}"
+
+          if [ "${{ matrix.gpu_arch }}" = "gfx942" ]; then
+            rocm_tag="rocm700-mi30x"
+          elif [ "${{ matrix.gpu_arch }}" = "gfx950" ]; then
+            rocm_tag="rocm700-mi35x"
+          else
+            echo "Unsupported gfx arch"
+            exit 1
+          fi
+
+          tag=v${version}-${rocm_tag}
+          echo "IMAGE_TAG=${tag}-${{ env.DATE }}" >> $GITHUB_ENV
+
+          docker build . -f docker/rocm.Dockerfile --build-arg SGL_BRANCH=${{ github.ref_name }} --build-arg BUILD_TYPE=${{ matrix.build_type }} --build-arg GPU_ARCH=${{ matrix.gpu_arch }} --build-arg ENABLE_MORI=1 --build-arg NIC_BACKEND=ainic --build-arg SETUPTOOLS_SCM_PRETEND_VERSION=${pretend_version} -t rocm/sgl-dev:${tag}-${{ env.DATE }} --no-cache
+          docker push rocm/sgl-dev:${tag}-${{ env.DATE }}
+
+      - name: Login to Docker Hub (lmsys)
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Push to lmsysorg/sglang-rocm
+        run: |
+          docker tag rocm/sgl-dev:${{ env.IMAGE_TAG }} lmsysorg/sglang-rocm:${{ env.IMAGE_TAG }}
+          docker push lmsysorg/sglang-rocm:${{ env.IMAGE_TAG }}
+
+  # Temporarily disable docker cache seeding until performant storage is in place
+  cache:
+    if: false
+    # if: always() && github.repository == 'sgl-project/sglang'
+    runs-on: linux-mi300-gpu-1
+    environment: 'prod'
+    needs: publish
+    strategy:
+      fail-fast: false
+      matrix:
+        gpu_arch: ['gfx942']
+        build_type: ['all']
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0  # Required for git describe to find tags
+
+      - name: "Set Date"
+        run: |
+          echo "DATE=$(date +%Y%m%d)" >> $GITHUB_ENV
+
+      - name: Get version from latest tag
+        id: version
+        run: |
+          # Get the latest version tag sorted by version number (e.g., v0.5.7 -> 0.5.7)
+          VERSION=$(git tag -l 'v[0-9]*' --sort=-v:refname | head -1 | sed 's/^v//')
+
+          if [ -z "$VERSION" ]; then
+            echo "::error::Could not determine version from git tags"
+            exit 1
+          fi
+
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+          echo "Detected version: ${VERSION}"
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_AMD_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_AMD_TOKEN }}
+
+      - name: Pull and Save Docker Image to Cache
+        run: |
+          set -euxo pipefail
+
+          version=${{ steps.version.outputs.version }}
+          echo "Version: ${version}"
+
+          if [ "${{ matrix.gpu_arch }}" = "gfx942" ]; then
+            rocm_tag="rocm700-mi30x"
+          else
+            echo "Unsupported gfx arch"
+            exit 1
+          fi
+
+          tag=v${version}-${rocm_tag}
+
+          if [ "${{ matrix.build_type }}" = "all" ]; then
+            tag_suffix=""
+          else
+            echo "Unsupported build type"
+            exit 1
+          fi
+
+          image="rocm/sgl-dev:${tag}-${{ env.DATE }}${tag_suffix}"
+
+          # Determine target cache file name based on ROCm variant
+          if [[ "${rocm_tag}" == rocm700* ]]; then
+            final_path="/home/runner/sgl-data/docker/image-700.tar"
+          else
+            echo "Unexpected ROCm tag: ${rocm_tag}"
+            exit 1
+          fi
+
+          tmp_path="${final_path}.tmp"
+
+          echo "Pulling image: ${image}"
+          docker pull "${image}"
+
+          echo "Saving to temp file: ${tmp_path}"
+          docker save "${image}" -o "${tmp_path}"
+
+          echo "Moving to final path: ${final_path}"
+          mv -f "${tmp_path}" "${final_path}"
+
+          echo "Cache populated successfully at ${final_path}"

third_party/sglang/.github/workflows/release-docker-amd-rocm720-nightly.yml

@@ -0,0 +1,94 @@
+name: Release Docker Images ROCm 7.2.0 Nightly Preview (AMD)
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: '0 12 * * *'
+
+concurrency:
+  # A PR number if a pull request and otherwise the commit hash. This cancels
+  # queued and in-progress runs for the same PR (presubmit) or commit
+  # (postsubmit). The workflow name is prepended to avoid conflicts between
+  # different workflows.
+  group: ${{ github.workflow }}-${{ github.event.number || github.sha }}
+  cancel-in-progress: True
+
+jobs:
+  publish:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: amd-docker-scale
+    environment: 'prod'
+    strategy:
+      fail-fast: false
+      matrix:
+        gpu_arch: ['gfx942-rocm720', 'gfx950-rocm720']
+        build_type: ['all']
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0  # Required for git describe to find tags
+
+      - name: "Set Date"
+        run: |
+          echo "DATE=$(date +%Y%m%d)" >> $GITHUB_ENV
+
+      - name: Get version from latest tag
+        id: version
+        run: |
+          # Get the latest version tag sorted by version number (e.g., v0.5.7 -> 0.5.7)
+          VERSION=$(git tag -l 'v[0-9]*' --sort=-v:refname | head -1 | sed 's/^v//')
+
+          if [ -z "$VERSION" ]; then
+            echo "::error::Could not determine version from git tags"
+            exit 1
+          fi
+
+          # Get short commit hash of current HEAD
+          COMMIT_HASH=$(git rev-parse --short HEAD)
+
+          # Compose pretend version for setuptools_scm: e.g., 0.5.8.post1.dev20260211+g1a2b3c4
+          PRETEND_VERSION="${VERSION}.dev${{ env.DATE }}+g${COMMIT_HASH}"
+
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+          echo "pretend_version=${PRETEND_VERSION}" >> $GITHUB_OUTPUT
+          echo "Detected version: ${VERSION}"
+          echo "Pretend version for pip: ${PRETEND_VERSION}"
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_AMD_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_AMD_TOKEN }}
+
+      - name: Build and Push to rocm/sgl-dev
+        run: |
+          version=${{ steps.version.outputs.version }}
+          pretend_version=${{ steps.version.outputs.pretend_version }}
+          echo "Version: ${version}"
+          echo "Pretend version: ${pretend_version}"
+
+          if [ "${{ matrix.gpu_arch }}" = "gfx942-rocm720" ]; then
+            rocm_tag="rocm720-mi30x"
+          elif [ "${{ matrix.gpu_arch }}" = "gfx950-rocm720" ]; then
+            rocm_tag="rocm720-mi35x"
+          else
+            echo "Unsupported gfx arch"
+            exit 1
+          fi
+
+          tag=v${version}-${rocm_tag}
+          echo "IMAGE_TAG=${tag}-${{ env.DATE }}" >> $GITHUB_ENV
+
+          docker build . -f docker/rocm.Dockerfile --build-arg SGL_BRANCH=${{ github.ref_name }} --build-arg BUILD_TYPE=${{ matrix.build_type }} --build-arg GPU_ARCH=${{ matrix.gpu_arch }} --build-arg ENABLE_MORI=1 --build-arg NIC_BACKEND=ainic --build-arg SETUPTOOLS_SCM_PRETEND_VERSION=${pretend_version} -t rocm/sgl-dev:${tag}-${{ env.DATE }} --no-cache
+          docker push rocm/sgl-dev:${tag}-${{ env.DATE }}
+
+      - name: Login to Docker Hub (lmsys)
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Push to lmsysorg/sglang-rocm
+        run: |
+          docker tag rocm/sgl-dev:${{ env.IMAGE_TAG }} lmsysorg/sglang-rocm:${{ env.IMAGE_TAG }}
+          docker push lmsysorg/sglang-rocm:${{ env.IMAGE_TAG }}

third_party/sglang/.github/workflows/release-docker-amd.yml

@@ -0,0 +1,88 @@
+name: Release Docker Images (AMD)
+on:
+  push:
+    tags:
+      - 'v[0-9]+.*'
+  workflow_dispatch:
+    inputs:
+      version:
+        description: 'Version to build (without v prefix, e.g., 0.5.7)'
+        required: true
+
+jobs:
+  publish:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: amd-docker-scale
+    environment: 'prod'
+    strategy:
+      matrix:
+        rocm_version: ['rocm700', 'rocm720']
+        gpu_arch: ['gfx942', 'gfx950']
+        build_type: ['all']
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Get version from tag
+        id: version
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            VERSION="${{ github.event.inputs.version }}"
+          else
+            # Extract version from tag (e.g., v0.5.7 -> 0.5.7)
+            VERSION="${GITHUB_REF_NAME#v}"
+          fi
+
+          # Validate version format
+          if [ -z "$VERSION" ]; then
+            echo "::error::Version is empty"
+            exit 1
+          fi
+          if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::Invalid version format: $VERSION (expected: X.Y.Z)"
+            exit 1
+          fi
+
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+
+      - name: Build and Push
+        run: |
+          version=${{ steps.version.outputs.version }}
+          echo "Version: ${version}"
+
+          gpu_arch_suffix=""
+          if [ "${{ matrix.rocm_version }}" = "rocm700" ]; then
+            if [ "${{ matrix.gpu_arch }}" = "gfx942" ]; then
+              rocm_tag="rocm700-mi30x"
+            elif [ "${{ matrix.gpu_arch }}" = "gfx950" ]; then
+              rocm_tag="rocm700-mi35x"
+            else
+              echo "Unsupported gfx arch"
+              exit 1
+            fi
+          elif [ "${{ matrix.rocm_version }}" = "rocm720" ]; then
+            gpu_arch_suffix="-${{ matrix.rocm_version }}"
+            if [ "${{ matrix.gpu_arch }}" = "gfx942" ]; then
+              rocm_tag="rocm720-mi30x"
+            elif [ "${{ matrix.gpu_arch }}" = "gfx950" ]; then
+              rocm_tag="rocm720-mi35x"
+            else
+              echo "Unsupported gfx arch"
+              exit 1
+            fi
+          else
+            echo "Unsupported rocm version"
+            exit 1
+          fi
+
+          tag=v${version}-${rocm_tag}
+
+          # rocm.Dockerfile expects SGL_BRANCH with 'v' prefix for git tag checkout
+          docker build . -f docker/rocm.Dockerfile --build-arg BUILD_TYPE=${{ matrix.build_type }} --build-arg GPU_ARCH=${{ matrix.gpu_arch }}${gpu_arch_suffix} --build-arg SGL_BRANCH=v${version} --build-arg ENABLE_MORI=1 --build-arg NIC_BACKEND=ainic -t lmsysorg/sglang:${tag} --no-cache
+          docker push lmsysorg/sglang:${tag}

third_party/sglang/.github/workflows/release-docker-cu13-framework.yml

@@ -0,0 +1,190 @@
+name: Release CUDA 13 Framework Docker Images (Temporary)
+
+# Temporary workflow to build only versioned cu13 framework images
+# Can be deleted after use
+
+on:
+  workflow_dispatch:
+    inputs:
+      version:
+        description: "Version to build (without v prefix, e.g., 0.5.8)"
+        required: true
+jobs:
+  publish-x86:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: x64-docker-build-node
+    steps:
+      - name: Delete huge unnecessary tools folder
+        run: rm -rf /opt/hostedtoolcache
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Free disk space
+        uses: jlumbroso/free-disk-space@main
+        with:
+          tool-cache: false
+          docker-images: false
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          swap-storage: false
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Validate version
+        id: version
+        run: |
+          VERSION="${{ github.event.inputs.version }}"
+          if [ -z "$VERSION" ]; then
+            echo "::error::Version is empty"
+            exit 1
+          fi
+          if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::Invalid version format: $VERSION (expected: X.Y.Z)"
+            exit 1
+          fi
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+
+      - name: Build and Push AMD64 Framework (CUDA 13)
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          docker buildx build \
+            --target framework \
+            --platform linux/amd64 \
+            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
+            -f docker/Dockerfile \
+            --build-arg CUDA_VERSION=13.0.1 \
+            --build-arg BUILD_TYPE=all \
+            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
+            --build-arg GRACE_BLACKWELL=0 \
+            --build-arg SGL_VERSION=${version} \
+            --metadata-file /tmp/metadata.json \
+            --no-cache \
+            .
+
+          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata.json'))['containerimage.digest'])")
+          echo "Pushed digest: ${DIGEST}"
+          echo "${DIGEST}" > /tmp/digest-cu130-amd64-framework.txt
+
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digest-cu130-amd64
+          path: /tmp/digest-cu130-amd64-framework.txt
+          retention-days: 1
+
+  publish-arm64:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: arm-docker-build-node
+    steps:
+      - name: Delete huge unnecessary tools folder
+        run: rm -rf /opt/hostedtoolcache
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Validate version
+        id: version
+        run: |
+          VERSION="${{ github.event.inputs.version }}"
+          if [ -z "$VERSION" ]; then
+            echo "::error::Version is empty"
+            exit 1
+          fi
+          if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::Invalid version format: $VERSION (expected: X.Y.Z)"
+            exit 1
+          fi
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+
+      - name: Build and Push ARM64 Framework (CUDA 13)
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          docker buildx build \
+            --target framework \
+            --platform linux/arm64 \
+            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
+            -f docker/Dockerfile \
+            --build-arg CUDA_VERSION=13.0.1 \
+            --build-arg BUILD_TYPE=all \
+            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
+            --build-arg GRACE_BLACKWELL=1 \
+            --build-arg SGL_VERSION=${version} \
+            --metadata-file /tmp/metadata.json \
+            --no-cache \
+            .
+
+          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata.json'))['containerimage.digest'])")
+          echo "Pushed digest: ${DIGEST}"
+          echo "${DIGEST}" > /tmp/digest-cu130-arm64-framework.txt
+
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digest-cu130-arm64
+          path: /tmp/digest-cu130-arm64-framework.txt
+          retention-days: 1
+
+  create-manifest:
+    runs-on: ubuntu-22.04
+    needs: [publish-x86, publish-arm64]
+    if: github.repository == 'sgl-project/sglang'
+    steps:
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Download amd64 digest
+        uses: actions/download-artifact@v4
+        with:
+          name: digest-cu130-amd64
+          path: /tmp/digests/amd64
+
+      - name: Download arm64 digest
+        uses: actions/download-artifact@v4
+        with:
+          name: digest-cu130-arm64
+          path: /tmp/digests/arm64
+
+      - name: Create multi-arch manifest
+        run: |
+          version=${{ github.event.inputs.version }}
+          AMD64_DIGEST=$(cat /tmp/digests/amd64/digest-cu130-amd64-framework.txt)
+          ARM64_DIGEST=$(cat /tmp/digests/arm64/digest-cu130-arm64-framework.txt)
+
+          # Create versioned CUDA 13 framework manifest
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:v${version}-cu130 \
+            lmsysorg/sglang@${AMD64_DIGEST} \
+            lmsysorg/sglang@${ARM64_DIGEST}
+
+          # Create latest CUDA 13 framework manifest
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:latest-cu130 \
+            lmsysorg/sglang@${AMD64_DIGEST} \
+            lmsysorg/sglang@${ARM64_DIGEST}

third_party/sglang/.github/workflows/release-docker-dev.yml

@@ -0,0 +1,209 @@
+name: Build and Push Development Docker Images
+
+on:
+  workflow_dispatch:
+    inputs:
+      pr_number:
+        description: "PR number to build from (leave empty to use current branch)"
+        required: false
+        default: ""
+      tag:
+        description: "Custom tag suffix (overrides pr_number in tag). E.g. 'my-test' → dev-my-test, dev-cu13-my-test, etc."
+        required: false
+        default: ""
+  schedule:
+    - cron: "0 0 * * *"
+
+concurrency:
+  group: release-docker-dev-${{ inputs.tag || inputs.pr_number || 'nightly' }}
+  cancel-in-progress: true
+
+jobs:
+  build-dev:
+    if: ${{ github.repository == 'sgl-project/sglang' }}
+    runs-on: ${{ matrix.runner }}
+    strategy:
+      matrix:
+        include:
+          - runner: x64-docker-build-node
+            platform: linux/amd64
+            build_type: all
+            grace_blackwell: 0
+            arch_tag: x86
+            version: 12.9.1
+          - runner: arm-docker-build-node
+            platform: linux/arm64
+            build_type: all
+            grace_blackwell: 1
+            arch_tag: arm64
+            version: 12.9.1
+          - runner: x64-docker-build-node
+            platform: linux/amd64
+            build_type: all
+            grace_blackwell: 0
+            arch_tag: x86-cu13
+            version: 13.0.1
+          - runner: arm-docker-build-node
+            platform: linux/arm64
+            build_type: all
+            grace_blackwell: 1
+            arch_tag: arm64-cu13
+            version: 13.0.1
+    steps:
+      - name: Delete huge unnecessary tools folder
+        run: rm -rf /opt/hostedtoolcache
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || github.ref }}
+
+      - name: Free disk space
+        uses: jlumbroso/free-disk-space@main
+        with:
+          tool-cache: true
+          docker-images: true
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          swap-storage: true
+
+      - name: Prune Docker to reclaim disk space
+        run: |
+          docker buildx prune --filter "until=72h" -f
+          docker system prune -af --filter "until=72h"
+          docker volume prune -af
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Build and Push Dev Image
+        run: |
+          # Nightly (schedule) installs latest release; manual dispatch builds from checked-out source
+          if [ "${{ github.event_name }}" = "schedule" ]; then
+            SOURCE_ARG="--build-arg USE_LATEST_SGLANG=1"
+          else
+            SOURCE_ARG="--build-arg BRANCH_TYPE=local"
+          fi
+
+          docker buildx build \
+            --platform ${{ matrix.platform }} \
+            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
+            --target framework \
+            -f docker/Dockerfile \
+            --build-arg CUDA_VERSION=${{ matrix.version }} \
+            --build-arg BUILD_TYPE=${{ matrix.build_type }} \
+            --build-arg CMAKE_BUILD_PARALLEL_LEVEL=$(nproc) \
+            --build-arg GRACE_BLACKWELL=${{ matrix.grace_blackwell }} \
+            ${SOURCE_ARG} \
+            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
+            --metadata-file /tmp/metadata.json \
+            --no-cache \
+            .
+
+          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata.json'))['containerimage.digest'])")
+          echo "Pushed digest: ${DIGEST}"
+          echo "${DIGEST}" > /tmp/digest.txt
+
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digest-${{ matrix.arch_tag }}
+          path: /tmp/digest.txt
+          retention-days: 1
+
+  create-manifests:
+    runs-on: ubuntu-22.04
+    needs: [build-dev]
+    if: ${{ github.repository == 'sgl-project/sglang' }}
+    strategy:
+      matrix:
+        variant:
+          - base: dev
+            x86: x86
+            arm64: arm64
+          - base: dev-cu13
+            x86: x86-cu13
+            arm64: arm64-cu13
+    steps:
+      - uses: docker/setup-buildx-action@v3
+
+      - uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Download x86 digest
+        uses: actions/download-artifact@v4
+        with:
+          name: digest-${{ matrix.variant.x86 }}
+          path: /tmp/digests/x86
+
+      - name: Download arm64 digest
+        uses: actions/download-artifact@v4
+        with:
+          name: digest-${{ matrix.variant.arm64 }}
+          path: /tmp/digests/arm64
+
+      - name: Create multi-arch manifest
+        run: |
+          X86_DIGEST=$(cat /tmp/digests/x86/digest.txt)
+          ARM64_DIGEST=$(cat /tmp/digests/arm64/digest.txt)
+
+          SUFFIX=""
+          if [ -n "${{ inputs.tag }}" ]; then
+            SUFFIX="-${{ inputs.tag }}"
+          elif [ -n "${{ inputs.pr_number }}" ]; then
+            SUFFIX="-pr-${{ inputs.pr_number }}"
+          fi
+
+          TAG="${{ matrix.variant.base }}${SUFFIX}"
+
+          # For nightly (no suffix), also stamp a dated tag
+          EXTRA_TAG=""
+          if [ -z "${SUFFIX}" ]; then
+            SHORT_SHA="${{ github.sha }}"
+            EXTRA_TAG="-t lmsysorg/sglang:nightly-${TAG}-$(date +%Y%m%d)-${SHORT_SHA:0:8}"
+          fi
+
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:${TAG} \
+            ${EXTRA_TAG} \
+            lmsysorg/sglang@${X86_DIGEST} \
+            lmsysorg/sglang@${ARM64_DIGEST}
+
+          echo "✓ Published lmsysorg/sglang:${TAG}"
+
+      - name: Cleanup Old Nightly Builds
+        if: ${{ !inputs.tag && !inputs.pr_number }}
+        run: |
+          TOKEN=$(curl -s -H "Content-Type: application/json" \
+            -X POST -d '{"username": "${{ secrets.DOCKERHUB_USERNAME }}", "password": "${{ secrets.DOCKERHUB_TOKEN }}"}' \
+            https://hub.docker.com/v2/users/login/ | jq -r .token)
+
+          TAGS_RESPONSE=$(curl -s -H "Authorization: JWT $TOKEN" \
+            "https://hub.docker.com/v2/repositories/lmsysorg/sglang/tags/?page_size=100")
+
+          TAGS=$(echo "$TAGS_RESPONSE" | jq -r \
+            '.results[] | select(.name | test("^nightly-${{ matrix.variant.base }}-[0-9]")) | "\(.last_updated)|\(.name)"' \
+            | sort -r | cut -d'|' -f2)
+
+          TAG_COUNT=$(echo "$TAGS" | wc -l)
+          if [ "$TAG_COUNT" -gt 14 ]; then
+            echo "Found $TAG_COUNT nightly builds, keeping only the 14 most recent"
+            TAGS_TO_DELETE=$(echo "$TAGS" | tail -n +15)
+            for tag in $TAGS_TO_DELETE; do
+              echo "Deleting tag: $tag"
+              curl -X DELETE -H "Authorization: JWT $TOKEN" \
+                "https://hub.docker.com/v2/repositories/lmsysorg/sglang/tags/$tag/"
+            done
+          else
+            echo "Only $TAG_COUNT nightly builds found, no cleanup needed"
+          fi

third_party/sglang/.github/workflows/release-docker-gateway.yml

@@ -0,0 +1,39 @@
+name: Release SGLang Model Gateway Docker Image
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - sgl-model-gateway/bindings/python/pyproject.toml
+  workflow_dispatch:
+
+jobs:
+  publish:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Build and Push
+        run: |
+          version=$(cat sgl-model-gateway/bindings/python/src/sglang_router/version.py | cut -d'"' -f2)
+          tag=v${version}
+
+          docker buildx build . -f docker/gateway.Dockerfile \
+            --platform linux/amd64,linux/arm64 \
+            -t lmsysorg/sgl-model-gateway:${tag} \
+            -t lmsysorg/sgl-model-gateway:latest \
+            --push

third_party/sglang/.github/workflows/release-docker-npu-nightly.yml

@@ -0,0 +1,85 @@
+name: Release Docker Images Nightly (NPU)
+on:
+  pull_request:
+    branches:
+      - 'main'
+    paths:
+      - '.github/workflows/release-docker-npu-nightly.yml'
+      - 'docker/npu.Dockerfile'
+  workflow_dispatch:
+  schedule:
+    - cron: "0 16 * * *" # Execute at 0:00 a.m. Beijing Time every day
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.sha }}
+  cancel-in-progress: true
+
+jobs:
+  build:
+    runs-on: ubuntu-22.04-arm
+    strategy:
+      matrix:
+        cann_version: ["8.5.0"]
+        device_type: ["910b", "a3"]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Free up disk space
+        uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
+        with:
+          tool-cache: true
+          docker-images: false
+
+      - name: Setup Docker buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            lmsysorg/sglang
+          # push with schedule event
+          # push with workflow_dispatch event
+          tags: |
+            type=ref,event=pr
+            type=ref,event=branch
+            type=schedule,pattern=main
+          flavor: |
+            latest=false
+            suffix=-cann${{ matrix.cann_version }}-${{ matrix.device_type }},onlatest=true
+      # Login against a Docker registry except on PR
+      # https://github.com/docker/login-action
+      - name: Log into docker hub
+        uses: docker/login-action@v3
+        if: ${{ github.repository == 'sgl-project/sglang' && github.event_name != 'pull_request' }}
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      # Enable Docker multi-architecture build environment
+      # Emulate non-native architectures
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+      # Required for building and pushing multi-arch Docker images
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      # Build and push Docker image with Buildx (don't push on PR)
+      # https://github.com/docker/build-push-action
+      - name: Build and push Docker image
+        id: build-and-push
+        uses: docker/build-push-action@v6
+        with:
+          context: docker
+          file: docker/npu.Dockerfile
+          platforms: linux/arm64,linux/amd64
+          labels: ${{ steps.meta.outputs.labels }}
+          tags: ${{ steps.meta.outputs.tags }}
+          push: ${{ github.repository == 'sgl-project/sglang' && github.event_name != 'pull_request' }}
+          provenance: false
+          build-args: |
+            SGLANG_KERNEL_NPU_TAG=2026.03.10.rc1
+            CANN_VERSION=${{ matrix.cann_version }}
+            DEVICE_TYPE=${{ matrix.device_type }}

third_party/sglang/.github/workflows/release-docker-npu.yml

@@ -0,0 +1,93 @@
+name: Release Docker Images (NPU)
+on:
+  push:
+    tags:
+      - 'v[0-9]+.*'
+  workflow_dispatch:
+    inputs:
+      version:
+        description: 'Version to build (without v prefix, e.g., 0.5.7)'
+        required: true
+
+jobs:
+  build:
+    runs-on: ubuntu-22.04-arm
+    strategy:
+      matrix:
+        cann_version: ["8.5.0"]
+        device_type: ["910b", "a3"]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Free up disk space
+        uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
+        with:
+          tool-cache: true
+          docker-images: false
+
+        # push with tag
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            lmsysorg/sglang
+          tags: |
+            type=ref,event=pr
+          flavor: |
+            latest=false
+
+      # Login against a Docker registry except on PR
+      # https://github.com/docker/login-action
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        if: ${{ github.repository == 'sgl-project/sglang' && github.event_name != 'pull_request' }}
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Get version from tag
+        id: version
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            VERSION="${{ github.event.inputs.version }}"
+          else
+            # Extract version from tag (e.g., v0.5.7 -> 0.5.7)
+            VERSION="${GITHUB_REF_NAME#v}"
+          fi
+          # Validate version format
+          if [ -z "$VERSION" ]; then
+            echo "::error::Version is empty"
+            exit 1
+          fi
+          if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::Invalid version format: $VERSION (expected: X.Y.Z)"
+            exit 1
+          fi
+          echo "version=v${VERSION}" >> $GITHUB_OUTPUT
+          echo "TAG=lmsysorg/sglang:v${VERSION}-cann${{ matrix.cann_version }}-${{ matrix.device_type }}" >> $GITHUB_OUTPUT
+      # Enable Docker multi-architecture build environment
+      # Emulate non-native architectures
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+      # Required for building and pushing multi-arch Docker images
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build and push Docker image
+        id: build-and-push
+        uses: docker/build-push-action@v6
+        with:
+          context: docker
+          file: docker/npu.Dockerfile
+          platforms: linux/arm64,linux/amd64
+          labels: ${{ steps.meta.outputs.labels }}
+          tags: ${{ steps.meta.outputs.tags || steps.version.outputs.TAG }}
+          push: ${{ github.repository == 'sgl-project/sglang' && github.event_name != 'pull_request' }}
+          provenance: false
+          build-args: |
+            SGLANG_KERNEL_NPU_TAG=2026.03.10.rc1
+            CANN_VERSION=${{ matrix.cann_version }}
+            DEVICE_TYPE=${{ matrix.device_type }}
+            SGLANG_TAG=${{ steps.version.outputs.version }}

third_party/sglang/.github/workflows/release-docker-runtime.yml

@@ -0,0 +1,309 @@
+name: Release Docker Runtime Images
+#
+# This workflow builds and publishes runtime Docker images (production-optimized, ~50% smaller):
+#   - lmsysorg/sglang:v{version}-runtime, lmsysorg/sglang:latest-runtime
+#   - lmsysorg/sglang:v{version}-cu130-runtime, lmsysorg/sglang:latest-cu130-runtime
+#
+on:
+  push:
+    tags:
+      - "v[0-9]+.*"
+  workflow_dispatch:
+    inputs:
+      version:
+        description: "Version to build (without v prefix, e.g., 0.5.7)"
+        required: true
+
+jobs:
+  publish-x86:
+    if: github.repository == 'sgl-project/sglang'
+    environment: "prod"
+    strategy:
+      matrix:
+        variant:
+          - cuda_version: "12.9.1"
+            build_type: "all"
+            grace_blackwell: 0
+    runs-on: x64-docker-build-node
+    steps:
+      - name: Delete huge unnecessary tools folder
+        run: rm -rf /opt/hostedtoolcache
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Free disk space
+        uses: jlumbroso/free-disk-space@main
+        with:
+          tool-cache: false
+          docker-images: false
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          swap-storage: false
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Get version from tag
+        id: version
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            VERSION="${{ github.event.inputs.version }}"
+          else
+            # Extract version from tag (e.g., v0.5.7 -> 0.5.7)
+            VERSION="${GITHUB_REF_NAME#v}"
+          fi
+
+          # Validate version format
+          if [ -z "$VERSION" ]; then
+            echo "::error::Version is empty"
+            exit 1
+          fi
+          if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::Invalid version format: $VERSION (expected: X.Y.Z)"
+            exit 1
+          fi
+
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+
+      - name: Build and Push AMD64 Runtime
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          docker buildx build \
+            --target runtime \
+            --platform linux/amd64 \
+            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
+            -f docker/Dockerfile \
+            --build-arg CUDA_VERSION=${{ matrix.variant.cuda_version }} \
+            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
+            --build-arg GRACE_BLACKWELL=${{ matrix.variant.grace_blackwell }} \
+            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
+            --build-arg SGL_VERSION=${version} \
+            --metadata-file /tmp/metadata-cu129-runtime.json \
+            --no-cache \
+            .
+
+          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu129-runtime.json'))['containerimage.digest'])")
+          echo "Pushed digest: ${DIGEST}"
+          echo "${DIGEST}" > /tmp/digest-cu129-amd64-runtime.txt
+
+      - name: Build and Push AMD64 Runtime (CUDA 13)
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          docker buildx build \
+            --target runtime \
+            --platform linux/amd64 \
+            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
+            -f docker/Dockerfile \
+            --build-arg CUDA_VERSION=13.0.1 \
+            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
+            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
+            --build-arg GRACE_BLACKWELL=0 \
+            --build-arg SGL_VERSION=${version} \
+            --metadata-file /tmp/metadata-cu130-runtime.json \
+            --no-cache \
+            .
+
+          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu130-runtime.json'))['containerimage.digest'])")
+          echo "Pushed digest: ${DIGEST}"
+          echo "${DIGEST}" > /tmp/digest-cu130-amd64-runtime.txt
+
+      - name: Upload digests
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-amd64
+          path: /tmp/digest-*.txt
+          retention-days: 1
+
+  publish-arm64:
+    if: github.repository == 'sgl-project/sglang'
+    environment: "prod"
+    strategy:
+      matrix:
+        variant:
+          - cuda_version: "12.9.1"
+            build_type: "all"
+            grace_blackwell: 1
+    runs-on: arm-docker-build-node
+    steps:
+      - name: Delete huge unnecessary tools folder
+        run: rm -rf /opt/hostedtoolcache
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Get version from tag
+        id: version
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            VERSION="${{ github.event.inputs.version }}"
+          else
+            # Extract version from tag (e.g., v0.5.7 -> 0.5.7)
+            VERSION="${GITHUB_REF_NAME#v}"
+          fi
+
+          # Validate version format
+          if [ -z "$VERSION" ]; then
+            echo "::error::Version is empty"
+            exit 1
+          fi
+          if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::Invalid version format: $VERSION (expected: X.Y.Z)"
+            exit 1
+          fi
+
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+
+      - name: Build and Push ARM64 Runtime
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          docker buildx build \
+            --target runtime \
+            --platform linux/arm64 \
+            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
+            -f docker/Dockerfile \
+            --build-arg CUDA_VERSION=${{ matrix.variant.cuda_version }} \
+            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
+            --build-arg GRACE_BLACKWELL=${{ matrix.variant.grace_blackwell }} \
+            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
+            --build-arg SGL_VERSION=${version} \
+            --metadata-file /tmp/metadata-cu129-runtime.json \
+            --no-cache \
+            .
+
+          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu129-runtime.json'))['containerimage.digest'])")
+          echo "Pushed digest: ${DIGEST}"
+          echo "${DIGEST}" > /tmp/digest-cu129-arm64-runtime.txt
+
+      - name: Build and Push ARM64 Runtime (CUDA 13)
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          docker buildx build \
+            --target runtime \
+            --platform linux/arm64 \
+            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
+            -f docker/Dockerfile \
+            --build-arg CUDA_VERSION=13.0.1 \
+            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
+            --build-arg GRACE_BLACKWELL=1 \
+            --build-arg SGL_VERSION=${version} \
+            --metadata-file /tmp/metadata-cu130-runtime.json \
+            --no-cache \
+            .
+
+          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu130-runtime.json'))['containerimage.digest'])")
+          echo "Pushed digest: ${DIGEST}"
+          echo "${DIGEST}" > /tmp/digest-cu130-arm64-runtime.txt
+
+      - name: Upload digests
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-arm64
+          path: /tmp/digest-*.txt
+          retention-days: 1
+
+  create-manifests:
+    runs-on: ubuntu-22.04
+    needs: [publish-x86, publish-arm64]
+    if: github.repository == 'sgl-project/sglang'
+    environment: "prod"
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Get version from tag
+        id: version
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            VERSION="${{ github.event.inputs.version }}"
+          else
+            # Extract version from tag (e.g., v0.5.7 -> 0.5.7)
+            VERSION="${GITHUB_REF_NAME#v}"
+          fi
+
+          # Validate version format
+          if [ -z "$VERSION" ]; then
+            echo "::error::Version is empty"
+            exit 1
+          fi
+          if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::Invalid version format: $VERSION (expected: X.Y.Z)"
+            exit 1
+          fi
+
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+
+      - name: Download amd64 digests
+        uses: actions/download-artifact@v4
+        with:
+          name: digests-amd64
+          path: /tmp/digests/amd64
+
+      - name: Download arm64 digests
+        uses: actions/download-artifact@v4
+        with:
+          name: digests-arm64
+          path: /tmp/digests/arm64
+
+      - name: Create multi-arch manifests
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          CU129_AMD64_RT=$(cat /tmp/digests/amd64/digest-cu129-amd64-runtime.txt)
+          CU130_AMD64_RT=$(cat /tmp/digests/amd64/digest-cu130-amd64-runtime.txt)
+          CU129_ARM64_RT=$(cat /tmp/digests/arm64/digest-cu129-arm64-runtime.txt)
+          CU130_ARM64_RT=$(cat /tmp/digests/arm64/digest-cu130-arm64-runtime.txt)
+
+          # Create versioned runtime manifest
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:v${version}-runtime \
+            lmsysorg/sglang@${CU129_AMD64_RT} \
+            lmsysorg/sglang@${CU129_ARM64_RT}
+
+          # Create latest runtime manifest
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:latest-runtime \
+            lmsysorg/sglang@${CU129_AMD64_RT} \
+            lmsysorg/sglang@${CU129_ARM64_RT}
+
+          # Create versioned CUDA 13 runtime manifest
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:v${version}-cu130-runtime \
+            lmsysorg/sglang@${CU130_AMD64_RT} \
+            lmsysorg/sglang@${CU130_ARM64_RT}
+
+          # Create latest CUDA 13 runtime manifest
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:latest-cu130-runtime \
+            lmsysorg/sglang@${CU130_AMD64_RT} \
+            lmsysorg/sglang@${CU130_ARM64_RT}

third_party/sglang/.github/workflows/release-docker-xeon.yml

@@ -0,0 +1,62 @@
+name: Release Docker Xeon Images
+on:
+  push:
+    tags:
+      - 'v[0-9]+.*'
+  workflow_dispatch:
+    inputs:
+      version:
+        description: 'Version to build (without v prefix, e.g., 0.5.7)'
+        required: true
+
+jobs:
+  publish:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: ubuntu-24.04
+    environment: 'prod'
+    strategy:
+      matrix:
+        build_type: ['all']
+    steps:
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Get version from tag
+        id: version
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            VERSION="${{ github.event.inputs.version }}"
+          else
+            # Extract version from tag (e.g., v0.5.7 -> 0.5.7)
+            VERSION="${GITHUB_REF_NAME#v}"
+          fi
+
+          # Validate version format
+          if [ -z "$VERSION" ]; then
+            echo "::error::Version is empty"
+            exit 1
+          fi
+          if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::Invalid version format: $VERSION (expected: X.Y.Z)"
+            exit 1
+          fi
+
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+
+      - name: Build and Push
+        run: |
+          version=${{ steps.version.outputs.version }}
+          tag=v${version}-xeon
+
+          docker build . -f docker/xeon.Dockerfile \
+            --build-arg VER_SGLANG=v${version} \
+            -t lmsysorg/sglang:${tag} \
+            --no-cache
+          docker push lmsysorg/sglang:${tag}

third_party/sglang/.github/workflows/release-docker.yml

@@ -0,0 +1,294 @@
+name: Release Docker Images
+#
+# This workflow builds and publishes framework Docker images (full development environment):
+#   - lmsysorg/sglang:v{version}, lmsysorg/sglang:latest
+#   - lmsysorg/sglang:v{version}-cu130, lmsysorg/sglang:latest-cu130
+#
+on:
+  push:
+    tags:
+      - "v[0-9]+.*"
+  workflow_dispatch:
+    inputs:
+      version:
+        description: "Version to build (without v prefix, e.g., 0.5.7)"
+        required: true
+
+jobs:
+  publish-x86:
+    if: github.repository == 'sgl-project/sglang'
+    environment: "prod"
+    outputs:
+      digest-cu129: ${{ steps.build-cu129.outputs.digest }}
+      digest-cu130: ${{ steps.build-cu130.outputs.digest }}
+    strategy:
+      matrix:
+        variant:
+          - cuda_version: "12.9.1"
+            build_type: "all"
+            grace_blackwell: 0
+    runs-on: x64-docker-build-node
+    steps:
+      - name: Delete huge unnecessary tools folder
+        run: rm -rf /opt/hostedtoolcache
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Free disk space
+        uses: jlumbroso/free-disk-space@main
+        with:
+          tool-cache: false
+          docker-images: false
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          swap-storage: false
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Get version from tag
+        id: version
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            VERSION="${{ github.event.inputs.version }}"
+          else
+            # Extract version from tag (e.g., v0.5.7 -> 0.5.7)
+            VERSION="${GITHUB_REF_NAME#v}"
+          fi
+
+          # Validate version format
+          if [ -z "$VERSION" ]; then
+            echo "::error::Version is empty"
+            exit 1
+          fi
+          if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::Invalid version format: $VERSION (expected: X.Y.Z)"
+            exit 1
+          fi
+
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+
+      - name: Build AMD64 Framework
+        id: build-cu129
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          docker buildx build \
+            --target framework \
+            --platform linux/amd64 \
+            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
+            -f docker/Dockerfile \
+            --build-arg CUDA_VERSION=${{ matrix.variant.cuda_version }} \
+            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
+            --build-arg GRACE_BLACKWELL=${{ matrix.variant.grace_blackwell }} \
+            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
+            --build-arg SGL_VERSION=${version} \
+            --metadata-file /tmp/metadata-cu129-framework.json \
+            --no-cache \
+            .
+
+          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu129-framework.json'))['containerimage.digest'])")
+          echo "Pushed digest: ${DIGEST}"
+          echo "digest=${DIGEST}" >> $GITHUB_OUTPUT
+
+      - name: Build and Push AMD64 Framework (CUDA 13)
+        id: build-cu130
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          docker buildx build \
+            --target framework \
+            --platform linux/amd64 \
+            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
+            -f docker/Dockerfile \
+            --build-arg CUDA_VERSION=13.0.1 \
+            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
+            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
+            --build-arg GRACE_BLACKWELL=0 \
+            --build-arg SGL_VERSION=${version} \
+            --metadata-file /tmp/metadata-cu130-framework.json \
+            --no-cache \
+            .
+
+          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu130-framework.json'))['containerimage.digest'])")
+          echo "Pushed digest: ${DIGEST}"
+          echo "digest=${DIGEST}" >> $GITHUB_OUTPUT
+
+  publish-arm64:
+    if: github.repository == 'sgl-project/sglang'
+    environment: "prod"
+    outputs:
+      digest-cu129: ${{ steps.build-cu129.outputs.digest }}
+      digest-cu130: ${{ steps.build-cu130.outputs.digest }}
+    strategy:
+      matrix:
+        variant:
+          - cuda_version: "12.9.1"
+            build_type: "all"
+            grace_blackwell: 1
+    runs-on: arm-docker-build-node
+    steps:
+      - name: Delete huge unnecessary tools folder
+        run: rm -rf /opt/hostedtoolcache
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Get version from tag
+        id: version
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            VERSION="${{ github.event.inputs.version }}"
+          else
+            # Extract version from tag (e.g., v0.5.7 -> 0.5.7)
+            VERSION="${GITHUB_REF_NAME#v}"
+          fi
+
+          # Validate version format
+          if [ -z "$VERSION" ]; then
+            echo "::error::Version is empty"
+            exit 1
+          fi
+          if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::Invalid version format: $VERSION (expected: X.Y.Z)"
+            exit 1
+          fi
+
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+
+      - name: Build ARM64 Framework
+        id: build-cu129
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          docker buildx build \
+            --target framework \
+            --platform linux/arm64 \
+            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
+            -f docker/Dockerfile \
+            --build-arg CUDA_VERSION=${{ matrix.variant.cuda_version }} \
+            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
+            --build-arg GRACE_BLACKWELL=${{ matrix.variant.grace_blackwell }} \
+            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
+            --build-arg SGL_VERSION=${version} \
+            --metadata-file /tmp/metadata-cu129-framework.json \
+            --no-cache \
+            .
+
+          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu129-framework.json'))['containerimage.digest'])")
+          echo "Pushed digest: ${DIGEST}"
+          echo "digest=${DIGEST}" >> $GITHUB_OUTPUT
+
+      - name: Build and Push ARM64 Framework (CUDA 13)
+        id: build-cu130
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          docker buildx build \
+            --target framework \
+            --platform linux/arm64 \
+            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
+            -f docker/Dockerfile \
+            --build-arg CUDA_VERSION=13.0.1 \
+            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
+            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
+            --build-arg GRACE_BLACKWELL=1 \
+            --build-arg SGL_VERSION=${version} \
+            --metadata-file /tmp/metadata-cu130-framework.json \
+            --no-cache \
+            .
+
+          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu130-framework.json'))['containerimage.digest'])")
+          echo "Pushed digest: ${DIGEST}"
+          echo "digest=${DIGEST}" >> $GITHUB_OUTPUT
+
+  create-manifests:
+    runs-on: ubuntu-22.04
+    needs: [publish-x86, publish-arm64]
+    if: github.repository == 'sgl-project/sglang'
+    environment: "prod"
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Get version from tag
+        id: version
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            VERSION="${{ github.event.inputs.version }}"
+          else
+            # Extract version from tag (e.g., v0.5.7 -> 0.5.7)
+            VERSION="${GITHUB_REF_NAME#v}"
+          fi
+
+          # Validate version format
+          if [ -z "$VERSION" ]; then
+            echo "::error::Version is empty"
+            exit 1
+          fi
+          if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::Invalid version format: $VERSION (expected: X.Y.Z)"
+            exit 1
+          fi
+
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+
+      - name: Create multi-arch manifests
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          CU129_AMD64_FW=${{ needs.publish-x86.outputs.digest-cu129 }}
+          CU130_AMD64_FW=${{ needs.publish-x86.outputs.digest-cu130 }}
+          CU129_ARM64_FW=${{ needs.publish-arm64.outputs.digest-cu129 }}
+          CU130_ARM64_FW=${{ needs.publish-arm64.outputs.digest-cu130 }}
+
+          # Create versioned framework manifest (default)
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:v${version} \
+            lmsysorg/sglang@${CU129_AMD64_FW} \
+            lmsysorg/sglang@${CU129_ARM64_FW}
+
+          # Create latest framework manifest (default)
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:latest \
+            lmsysorg/sglang@${CU129_AMD64_FW} \
+            lmsysorg/sglang@${CU129_ARM64_FW}
+
+          # Create versioned CUDA 13 framework manifest
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:v${version}-cu130 \
+            lmsysorg/sglang@${CU130_AMD64_FW} \
+            lmsysorg/sglang@${CU130_ARM64_FW}
+
+          # Create latest CUDA 13 framework manifest
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:latest-cu130 \
+            lmsysorg/sglang@${CU130_AMD64_FW} \
+            lmsysorg/sglang@${CU130_ARM64_FW}

third_party/sglang/.github/workflows/release-docs.yml

@@ -0,0 +1,89 @@
+name: Release Documentation
+
+on:
+  release:
+    types: [published]
+  push:
+    branches:
+      - main
+    paths:
+      - "docs/**"
+      - "python/sglang/version.py"
+      - "python/sglang/**"
+  workflow_dispatch:
+
+concurrency:
+  group: release-docs-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  SGLANG_IS_IN_CI: true
+
+jobs:
+  execute-and-deploy:
+    runs-on: 1-gpu-h100
+    if: github.repository == 'sgl-project/sglang'
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Fetch full git history for release index
+        if: github.event_name == 'release'
+        run: |
+          git fetch --prune --unshallow || git fetch --prune --depth=0
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+          pip install -r docs/requirements.txt
+          apt-get update && apt-get install -y pandoc parallel retry
+          ln -sf "$(which python3)" /usr/bin/python
+
+      - name: Setup Jupyter Kernel
+        run: |
+          python -m ipykernel install --user --name python3 --display-name "Python 3"
+
+      - name: Execute notebooks
+        timeout-minutes: 40
+        run: |
+          cd docs
+          make clean
+          make compile
+
+      - name: Push HTML to sgl-project.github.io
+        timeout-minutes: 30
+        env:
+          GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_DOCUMENTATION }}
+        run: |
+          cd docs
+          make html
+          make markdown
+          python3 wrap_run_llm.py
+
+          if [[ "${{ github.event_name }}" == "release" ]]; then
+            python3 release_lookup/generate_index.py --output release_lookup/release_index.json
+
+            # Copy release lookup tool for official docs on published releases.
+            mkdir -p _build/html/release_lookup
+            cp release_lookup/index.html _build/html/release_lookup/
+            cp release_lookup/release_index.json _build/html/release_lookup/
+          fi
+
+          cd _build/html
+
+          git clone https://$GITHUB_TOKEN@github.com/sgl-project/sgl-project.github.io.git ../sgl-project.github.io --depth 1
+          if [[ "${{ github.event_name }}" == "release" ]]; then
+            find ../sgl-project.github.io/ -mindepth 1 -not -path "../sgl-project.github.io/.git*" -not -name CNAME -not -name ".jekyll" -not -name ".nojekyll" -delete
+          else
+            find ../sgl-project.github.io/ -mindepth 1 -not -path "../sgl-project.github.io/.git*" -not -path "../sgl-project.github.io/release_lookup*" -not -name CNAME -not -name ".jekyll" -not -name ".nojekyll" -delete
+          fi
+          cp -r * ../sgl-project.github.io
+          cp ../../README.md ../sgl-project.github.io/README.md
+          cd ../sgl-project.github.io
+          git config user.name "sglang-bot"
+          git config user.email "sglangbot@gmail.com"
+          git add .
+          git commit -m "Update $(date +'%Y-%m-%d %H:%M:%S')"
+          git push https://$GITHUB_TOKEN@github.com/sgl-project/sgl-project.github.io.git main
+          cd ..
+          rm -rf sgl-project.github.io

third_party/sglang/.github/workflows/release-pypi-gateway.yml

@@ -0,0 +1,167 @@
+name: Release SGLang Model Gateway to PyPI
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - sgl-model-gateway/bindings/python/pyproject.toml
+  workflow_dispatch:
+
+jobs:
+  build:
+    name: build on ${{ matrix.platform || matrix.os }} (${{ matrix.target }} - ${{ matrix.manylinux || 'auto' }})
+    runs-on: ${{ matrix.os }}-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu, macos, windows]
+        target: [x86_64, aarch64]
+        manylinux: [auto]
+        include:
+          - os: ubuntu
+            platform: linux
+          - os: windows
+            ls: dir
+            target: x86_64
+            python-architecture: x64
+            interpreter: 3.9 3.10 3.11 3.12 3.13
+          - os: macos
+            target: aarch64
+            interpreter: 3.9 3.10 3.11 3.12 3.13
+          - os: ubuntu
+            platform: linux
+            target: aarch64
+          # musllinux
+          - os: ubuntu
+            platform: linux
+            target: x86_64
+            manylinux: musllinux_1_1
+          - os: ubuntu
+            platform: linux
+            target: aarch64
+            manylinux: musllinux_1_1
+        exclude:
+          - os: windows
+            target: aarch64
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          path: sglang-repo
+
+      - name: Move sgl-model-gateway folder to root and delete sglang-repo
+        run: |
+          mv sglang-repo/sgl-model-gateway/* .
+          rm -rf sglang-repo
+          ls -alt
+        shell: bash
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.13"
+          architecture: ${{ matrix.python-architecture || 'x64' }}
+
+      - name: Install twine
+        run: pip install -U twine
+
+      - name: Install protoc (macOS)
+        if: matrix.os == 'macos'
+        run: brew install protobuf
+
+      - name: Install protoc (Windows)
+        if: matrix.os == 'windows'
+        run: choco install protoc -y
+
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          working-directory: bindings/python
+          target: ${{ matrix.target }}
+          manylinux: ${{ matrix.manylinux || 'auto' }}
+          args: --release --out dist --features vendored-openssl --interpreter ${{ matrix.interpreter || '3.9 3.10 3.11 3.12 3.13 3.14' }}
+          rust-toolchain: stable
+          docker-options: -e CI -e CC_aarch64_unknown_linux_gnu=aarch64-linux-gnu-gcc -e CXX_aarch64_unknown_linux_gnu=aarch64-linux-gnu-g++
+          before-script-linux: |
+            # Install build dependencies (perl/make for vendored OpenSSL, protoc for gRPC)
+            if command -v yum &> /dev/null; then
+              yum update -y && yum install -y wget unzip gcc gcc-c++ perl-core make
+              # Install cross-compilation toolchain for aarch64 if needed
+              if [ "${{ matrix.target }}" = "aarch64" ]; then
+                yum install -y gcc-aarch64-linux-gnu gcc-c++-aarch64-linux-gnu || true
+              fi
+            elif command -v apt-get &> /dev/null; then
+              apt-get update && apt-get install -y wget unzip gcc g++ perl make
+              # Install cross-compilation toolchain for aarch64 if needed
+              if [ "${{ matrix.target }}" = "aarch64" ]; then
+                apt-get install -y gcc-aarch64-linux-gnu g++-aarch64-linux-gnu || true
+              fi
+            fi
+            (cd /tmp && \
+             wget https://github.com/protocolbuffers/protobuf/releases/download/v32.0/protoc-32.0-linux-x86_64.zip && \
+             unzip protoc-32.0-linux-x86_64.zip -d /usr/local && \
+             rm protoc-32.0-linux-x86_64.zip)
+            protoc --version
+
+      - name: List built packages
+        run: ${{ matrix.ls || 'ls -lh' }} bindings/python/dist/
+
+      - name: Check packages
+        run: twine check --strict bindings/python/dist/*
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: packages-${{ matrix.os }}-${{ matrix.target }}-${{ matrix.manylinux || 'auto' }}
+          path: bindings/python/dist/
+
+  build-sdist:
+    name: Build SDist
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          path: sglang-repo
+
+      - name: Move sgl-model-gateway folder to root and delete sglang-repo
+        run: |
+          mv sglang-repo/sgl-model-gateway/* .
+          rm -rf sglang-repo
+          ls -alt
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.13"
+
+      - name: Build SDist
+        uses: PyO3/maturin-action@v1
+        with:
+          working-directory: bindings/python
+          command: sdist
+          args: --out dist
+          rust-toolchain: stable
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: sdist
+          path: bindings/python/dist/*.tar.gz
+
+  upload:
+    name: Upload to PyPI
+    if: github.repository == 'sgl-project/sglang'  # Ensure this job only runs for the sgl-project/sglang repository
+    needs: [build, build-sdist]
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          path: dist
+          merge-multiple: true
+
+      - name: Upload to PyPI
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN_ROUTER }}
+        run: |
+          pip install twine
+          twine upload dist/* --verbose

third_party/sglang/.github/workflows/release-pypi-nightly.yml

@@ -0,0 +1,169 @@
+name: Release PyPI Nightly Wheels
+
+on:
+  # Run daily at 2 AM UTC
+  schedule:
+    - cron: '0 2 * * *'
+  # Triggered by nightly Docker workflow to use same commit
+  repository_dispatch:
+    types: [nightly-release]
+  # Manual trigger for testing
+  workflow_dispatch:
+    inputs:
+      commit_sha:
+        description: 'Specific commit SHA to build (leave empty for latest)'
+        required: false
+        type: string
+      cuda_version:
+        description: 'CUDA version (e.g., 129 or 130)'
+        required: false
+        default: '129'
+        type: string
+
+concurrency:
+  group: release-pypi-nightly-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build-nightly-wheel:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: ubuntu-latest
+    outputs:
+      nightly_version: ${{ steps.build.outputs.nightly_version }}
+      commit_hash: ${{ steps.build.outputs.commit_hash }}
+      build_date: ${{ steps.build.outputs.build_date }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          # Use commit from: 1) Docker workflow, 2) manual input, 3) latest main
+          ref: ${{ github.event.client_payload.commit_sha || inputs.commit_sha || github.sha }}
+          fetch-depth: 0  # Need full history for setuptools-scm
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+
+      - name: Install build dependencies
+        run: |
+          pip install build wheel setuptools setuptools-scm
+
+      - name: Build wheel
+        id: build
+        run: |
+          cd python
+          cp ../README.md ../LICENSE .
+
+          # Parse git describe output to get latest tag
+          # Use same command as pyproject.toml to ensure version consistency
+          DESC=$(git tag --list --sort=-version:refname 'v*.*.*' | head -1 | xargs git describe --tags --long 2>/dev/null || echo 'v0.0.0-0-g0000000')
+          TAG=$(echo "$DESC" | cut -d- -f1)
+          HASH="g$(git rev-parse --short HEAD)"
+          BUILD_DATE=$(date -u +%Y%m%d)
+
+          # Increment patch version for nightlies (e.g., v0.5.9 -> 0.5.10)
+          # Must always increment so nightly > latest tag per PEP 440 ordering:
+          #   X.Y.Z.devN < X.Y.Z.rcN < X.Y.Z < X.Y.(Z+1).devN
+          VERSION=${TAG#v}  # Remove 'v' prefix
+          MAJOR=$(echo "$VERSION" | cut -d. -f1)
+          MINOR=$(echo "$VERSION" | cut -d. -f2)
+          PATCH_RAW=$(echo "$VERSION" | cut -d. -f3)
+          # Strip pre-release suffixes (rc0, post1, etc.) to get numeric patch
+          PATCH=$(echo "$PATCH_RAW" | sed 's/[^0-9].*//')
+          NEXT_PATCH=$((PATCH + 1))
+          NEXT_VERSION="${MAJOR}.${MINOR}.${NEXT_PATCH}"
+
+          # Use date-based dev number for correct chronological sorting
+          # e.g., 0.5.9.dev20260215+g4cf4f0859 > 0.5.9.dev20260214+g45a4697d4
+          FORCE_VERSION="${NEXT_VERSION}.dev${BUILD_DATE}+${HASH}"
+          echo "Forcing nightly version to: $FORCE_VERSION"
+          export SETUPTOOLS_SCM_PRETEND_VERSION="$FORCE_VERSION"
+
+          # Build wheel
+          python3 -m build --wheel
+
+          # Extract version from built wheel filename
+          WHEEL_FILE=$(ls dist/*.whl)
+          NIGHTLY_VERSION=$(echo "$WHEEL_FILE" | sed 's/.*sglang-\(.*\)-py3.*/\1/')
+
+          # Get commit info
+          COMMIT_HASH=$(git rev-parse --short HEAD)
+          BUILD_DATE=$(date -u +%Y-%m-%d)
+
+          echo "Built wheel: $WHEEL_FILE"
+          echo "Nightly version: ${NIGHTLY_VERSION}"
+          echo "Commit: ${COMMIT_HASH}"
+          echo "Build date: ${BUILD_DATE}"
+
+          echo "nightly_version=${NIGHTLY_VERSION}" >> $GITHUB_OUTPUT
+          echo "commit_hash=${COMMIT_HASH}" >> $GITHUB_OUTPUT
+          echo "build_date=${BUILD_DATE}" >> $GITHUB_OUTPUT
+
+      - name: Upload wheel artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: nightly-wheel
+          path: python/dist/*.whl
+          retention-days: 7
+
+  release-nightly:
+    needs: build-nightly-wheel
+    runs-on: ubuntu-latest
+    environment: 'prod'
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Download wheel artifact
+        uses: actions/download-artifact@v4
+        with:
+          name: nightly-wheel
+          path: dist/
+
+      - name: List downloaded wheels
+        run: |
+          echo "Downloaded wheel:"
+          ls -lh dist/
+
+      - name: Create GitHub Release for nightly wheel
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: nightly-${{ needs.build-nightly-wheel.outputs.build_date }}-${{ needs.build-nightly-wheel.outputs.commit_hash }}
+          name: Nightly Build ${{ needs.build-nightly-wheel.outputs.build_date }} (${{ needs.build-nightly-wheel.outputs.commit_hash }})
+          repository: sgl-project/whl
+          token: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
+          prerelease: true
+          body: |
+            Nightly build from commit ${{ github.sha }}
+            Build date: ${{ needs.build-nightly-wheel.outputs.build_date }}
+            Version: ${{ needs.build-nightly-wheel.outputs.nightly_version }}
+          files: |
+            dist/*.whl
+
+      - name: Clone wheel index repository
+        run: |
+          git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl
+          cd sgl-whl
+          git config --local user.name "sglang-bot"
+          git config --local user.email "sglangbot@gmail.com"
+        env:
+          WHL_TOKEN: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+
+      - name: Update wheel index
+        run: |
+          python3 scripts/update_nightly_whl_index.py \
+            --commit-hash ${{ needs.build-nightly-wheel.outputs.commit_hash }} \
+            --nightly-version ${{ needs.build-nightly-wheel.outputs.nightly_version }} \
+            --cuda-version ${{ inputs.cuda_version || '129' }} \
+            --build-date ${{ needs.build-nightly-wheel.outputs.build_date }}
+
+      - name: Push wheel index
+        run: |
+          cd sgl-whl
+          git add -A
+          git diff --staged --quiet || git commit -m "Update nightly wheel index for commit ${{ needs.build-nightly-wheel.outputs.commit_hash }}"
+          git push

third_party/sglang/.github/workflows/release-pypi-pr.yml

@@ -0,0 +1,183 @@
+name: Release PyPI PR Wheels
+
+on:
+  workflow_dispatch:
+    inputs:
+      pr_number:
+        description: 'PR number to build wheel for (works with both internal and fork PRs)'
+        required: true
+        type: string
+
+concurrency:
+  group: build-pr-wheel-${{ github.event.inputs.pr_number }}
+  cancel-in-progress: true
+
+jobs:
+  build-pr-wheel:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: ubuntu-latest
+    outputs:
+      wheel_version: ${{ steps.gen_version.outputs.wheel_version }}
+      commit_hash: ${{ steps.gen_version.outputs.commit_hash }}
+      build_date: ${{ steps.gen_version.outputs.build_date }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: refs/pull/${{ inputs.pr_number }}/head
+          fetch-depth: 0  # Need full history for version generation
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+
+      - name: Generate PR wheel version
+        id: gen_version
+        run: |
+          # Get base version from the latest v*.*.* git tag directly
+          # Note: We cannot use setuptools_scm here because the [tool.setuptools_scm]
+          # config (with custom git_describe_command) lives in python/pyproject.toml,
+          # not at the repo root. Without that config, setuptools_scm falls back to
+          # default git describe which finds gateway-* tags instead of v*.*.* release tags.
+          LATEST_TAG=$(git tag --list --sort=-version:refname 'v*.*.*' | head -1)
+          BASE_VERSION=${LATEST_TAG#v}
+          echo "Latest release tag: ${LATEST_TAG}"
+
+          # Get commit info
+          COMMIT_HASH=$(git rev-parse --short HEAD)
+          COMMIT_COUNT=$(git rev-list --count HEAD)
+
+          # Get current date in YYYY-MM-DD format
+          BUILD_DATE=$(date -u +%Y-%m-%d)
+
+          # Always use pr-{number} format for suffix
+          SUFFIX="pr-${{ inputs.pr_number }}"
+
+          # Generate PR wheel version following PEP 440
+          # Format: {base_version}.dev{commit_count}+pr-{number}.g{commit_hash}
+          WHEEL_VERSION="${BASE_VERSION}.dev${COMMIT_COUNT}+${SUFFIX}.g${COMMIT_HASH}"
+
+          echo "Base version: ${BASE_VERSION}"
+          echo "PR wheel version: ${WHEEL_VERSION}"
+          echo "Commit: ${COMMIT_HASH}"
+          echo "Build date: ${BUILD_DATE}"
+
+          echo "wheel_version=${WHEEL_VERSION}" >> $GITHUB_OUTPUT
+          echo "commit_hash=${COMMIT_HASH}" >> $GITHUB_OUTPUT
+          echo "base_version=${BASE_VERSION}" >> $GITHUB_OUTPUT
+          echo "build_date=${BUILD_DATE}" >> $GITHUB_OUTPUT
+
+      - name: Update pyproject.toml with PR wheel version
+        run: |
+          cd python
+          WHEEL_VERSION="${{ steps.gen_version.outputs.wheel_version }}"
+
+          # Update pyproject.toml to use static version instead of dynamic
+          # Remove 'version' from dynamic list and add static version
+          sed -i 's/dynamic = \["version"\]/dynamic = []/' pyproject.toml
+          sed -i "/^name = \"sglang\"/a version = \"${WHEEL_VERSION}\"" pyproject.toml
+
+          # Verify update
+          echo "Updated version in pyproject.toml:"
+          grep "^version" pyproject.toml
+          grep "^dynamic" pyproject.toml
+
+      - name: Install build dependencies
+        run: |
+          cd python
+          pip install build wheel setuptools
+
+      - name: Build wheel
+        run: |
+          cd python
+          cp ../README.md ../LICENSE .
+          python3 -m build --wheel
+
+          # List built wheels
+          echo "Built wheel:"
+          ls -lh dist/
+
+      - name: Upload wheel artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: pr-wheel-${{ inputs.pr_number }}
+          path: python/dist/*.whl
+          retention-days: 30
+
+  release-pr-wheel:
+    needs: build-pr-wheel
+    runs-on: ubuntu-latest
+    environment: 'prod'
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Download wheel artifact
+        uses: actions/download-artifact@v4
+        with:
+          name: pr-wheel-${{ inputs.pr_number }}
+          path: dist/
+
+      - name: List downloaded wheels
+        run: |
+          echo "Downloaded wheel:"
+          ls -lh dist/
+
+      - name: Create GitHub Release for PR wheel
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: pr-${{ inputs.pr_number }}-${{ needs.build-pr-wheel.outputs.build_date }}-${{ needs.build-pr-wheel.outputs.commit_hash }}
+          name: "PR #${{ inputs.pr_number }} Build (${{ needs.build-pr-wheel.outputs.commit_hash }})"
+          repository: sgl-project/whl
+          token: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
+          prerelease: true
+          body: |
+            PR wheel build from PR #${{ inputs.pr_number }}
+            Commit: ${{ github.sha }}
+            Build date: ${{ needs.build-pr-wheel.outputs.build_date }}
+            Version: ${{ needs.build-pr-wheel.outputs.wheel_version }}
+
+            **Installation via index (pip):**
+            ```bash
+            pip install sglang==${{ needs.build-pr-wheel.outputs.wheel_version }} --index-url https://sgl-project.github.io/whl/pr/
+            ```
+
+            **Installation via index (uv):**
+            ```bash
+            uv pip install sglang==${{ needs.build-pr-wheel.outputs.wheel_version }} --index-url https://sgl-project.github.io/whl/pr/ --extra-index-url https://pypi.org/simple --index-strategy unsafe-best-match
+            ```
+
+            **Direct installation:**
+            ```bash
+            pip install https://github.com/sgl-project/whl/releases/download/pr-${{ inputs.pr_number }}-${{ needs.build-pr-wheel.outputs.build_date }}-${{ needs.build-pr-wheel.outputs.commit_hash }}/sglang-${{ needs.build-pr-wheel.outputs.wheel_version }}-py3-none-any.whl
+            ```
+          files: |
+            dist/*.whl
+
+      - name: Clone wheel index repository
+        run: |
+          git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl
+          cd sgl-whl
+          git config --local user.name "sglang-bot"
+          git config --local user.email "sglangbot@gmail.com"
+        env:
+          WHL_TOKEN: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+
+      - name: Update wheel index
+        run: |
+          python3 scripts/update_pr_whl_index.py \
+            --pr-number ${{ inputs.pr_number }} \
+            --commit-hash ${{ needs.build-pr-wheel.outputs.commit_hash }} \
+            --wheel-version ${{ needs.build-pr-wheel.outputs.wheel_version }} \
+            --build-date ${{ needs.build-pr-wheel.outputs.build_date }}
+
+      - name: Push wheel index
+        run: |
+          cd sgl-whl
+          git add -A
+          git diff --staged --quiet || git commit -m "Update PR wheel index for PR #${{ inputs.pr_number }} (commit ${{ needs.build-pr-wheel.outputs.commit_hash }})"
+          git push

third_party/sglang/.github/workflows/release-pypi.yml

@@ -0,0 +1,31 @@
+name: Release PyPI
+on:
+  push:
+    tags:
+      - 'v[0-9]+.*'
+  workflow_dispatch:
+
+jobs:
+  publish:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: ubuntu-latest
+    environment: "prod"
+    steps:
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0  # Required for setuptools-scm to determine version from tags
+
+      - name: Upload to pypi
+        run: |
+          cd python
+          cp ../README.md ../LICENSE .
+          pip install build wheel setuptools setuptools-scm
+          python3 -m build
+          pip install twine
+          python3 -m twine upload dist/* -u __token__ -p ${{ secrets.PYPI_TOKEN }}

third_party/sglang/.github/workflows/release-tag.yml

@@ -0,0 +1,68 @@
+name: Release Tag
+# Creates a git tag to trigger release workflows (PyPI, Docker)
+# Use this after testing on a release branch is complete
+on:
+  workflow_dispatch:
+    inputs:
+      version:
+        description: 'Version to tag (without v prefix, e.g., 0.5.7)'
+        required: true
+        type: string
+      ref:
+        description: 'Branch or commit to tag (e.g., release/v0.5.7, main, or commit SHA)'
+        required: false
+        default: 'main'
+        type: string
+
+permissions:
+  contents: write
+
+jobs:
+  create-tag:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: ubuntu-latest
+    environment: 'prod'
+    steps:
+      - name: Validate version format
+        run: |
+          VERSION="${{ github.event.inputs.version }}"
+          if [ -z "$VERSION" ]; then
+            echo "::error::Version is required"
+            exit 1
+          fi
+          if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::Invalid version format: $VERSION (expected: X.Y.Z or X.Y.Z.postN)"
+            exit 1
+          fi
+          echo "Version validated: v$VERSION"
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.inputs.ref }}
+          fetch-depth: 0
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Check if tag already exists
+        run: |
+          TAG="v${{ github.event.inputs.version }}"
+          if git rev-parse "$TAG" >/dev/null 2>&1; then
+            echo "::error::Tag $TAG already exists"
+            exit 1
+          fi
+          echo "Tag $TAG does not exist, proceeding..."
+
+      - name: Create and push tag
+        run: |
+          TAG="v${{ github.event.inputs.version }}"
+          REF="${{ github.event.inputs.ref }}"
+
+          git config user.name "sglang-bot"
+          git config user.email "sglang-bot@users.noreply.github.com"
+
+          echo "Creating tag $TAG on ref $REF (commit: $(git rev-parse HEAD))"
+          git tag -a "$TAG" -m "Release $TAG"
+          git push origin "$TAG"
+
+          echo "::notice::Successfully created and pushed tag $TAG"
+          echo "This will trigger the release workflows (PyPI, Docker)"

third_party/sglang/.github/workflows/release-whl-kernel.yml

@@ -0,0 +1,440 @@
+name: Release SGLang Kernels
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - sgl-kernel/python/sgl_kernel/version.py
+  workflow_dispatch:
+    inputs:
+      target:
+        type: choice
+        description: 'Build target'
+        required: false
+        default: 'all'
+        options:
+          - 'all'
+          - 'cu129'
+          - 'cu130'
+          - 'rocm700'
+          - 'rocm720'
+          - 'musa43'
+      tag_name:
+        description: "Version number, must be in the form of vX.Y.Z (e.g. v0.4.0)"
+        type: string
+        required: false
+      pr_number:
+        description: "PR number to build from (e.g. 12345)"
+        type: string
+        required: false
+
+concurrency:
+  group: release-sglang-kernels-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build-cu129-matrix:
+    if: |
+      github.repository == 'sgl-project/sglang' &&
+      (github.event_name == 'push' || github.event.inputs.target == 'all' || github.event.inputs.target == 'cu129')
+    strategy:
+      matrix:
+        python-version: ["3.10"]
+        cuda-version: ["12.9"]
+        arch: [x86_64, aarch64]
+        include:
+          - arch: x86_64
+            runner: x64-kernel-build-node
+          - arch: aarch64
+            runner: arm-kernel-build-node
+    runs-on: ${{ matrix.runner }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Build wheels
+        run: |
+          cd sgl-kernel
+          chmod +x ./build.sh
+          ./build.sh "${{ matrix.python-version }}" "${{ matrix.cuda-version }}" ${{ matrix.arch == 'aarch64' && 'aarch64' || '' }}
+        env:
+          BUILD_JOBS: 64
+          NVCC_THREADS: 8
+
+      - name: Upload to PyPI
+        working-directory: sgl-kernel
+        run: |
+          pip install twine
+          python3 -m twine upload --skip-existing dist/* -u __token__ -p ${{ secrets.PYPI_TOKEN_SGLANG_KERNEL }}
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheel-python${{ matrix.python-version }}-cuda${{ matrix.cuda-version }}${{ matrix.arch == 'aarch64' && '-aarch64' || '' }}
+          path: sgl-kernel/dist/*
+
+  release-cu129:
+    needs: build-cu129-matrix
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}
+
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-*
+
+      - name: Set tag name
+        id: set_tag_name
+        run: |
+          if [ -z "${{ inputs.tag_name }}" ]; then
+            TAG_NAME="v$(cat sgl-kernel/python/sgl_kernel/version.py | cut -d'"' -f2)"
+            echo "tag_name=$TAG_NAME" >> $GITHUB_OUTPUT
+          else
+            echo "tag_name=${{ inputs.tag_name }}" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Release
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: ${{ steps.set_tag_name.outputs.tag_name }}
+          repository: sgl-project/whl
+          token: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
+          files: |
+            sgl-kernel/dist/*
+
+      - name: Clone wheel index
+        run: git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl
+        env:
+          WHL_TOKEN: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
+
+      - name: Update wheel index
+        run: python3 scripts/update_kernel_whl_index.py --cuda 129
+
+      - name: Push wheel index
+        run: |
+          cd sgl-whl
+          git config --local user.name "sglang-bot"
+          git config --local user.email "sglangbot@gmail.com"
+          git add -A
+          git commit -m "update whl index"
+          git push
+
+  # for now we do not release CUDA 13.0 wheels to pypi
+  build-cu130-matrix:
+    if: |
+      github.repository == 'sgl-project/sglang' &&
+      (github.event_name == 'push' || github.event.inputs.target == 'all' || github.event.inputs.target == 'cu130')
+    strategy:
+      matrix:
+        python-version: ["3.10"]
+        cuda-version: ["13.0"]
+        arch: [x86_64, aarch64]
+        include:
+          - arch: x86_64
+            runner: x64-kernel-build-node
+          - arch: aarch64
+            runner: arm-kernel-build-node
+    runs-on: ${{ matrix.runner }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Build wheels
+        run: |
+          cd sgl-kernel
+          chmod +x ./build.sh
+          ./build.sh "${{ matrix.python-version }}" "${{ matrix.cuda-version }}" ${{ matrix.arch == 'aarch64' && 'aarch64' || '' }}
+        env:
+          BUILD_JOBS: 64
+          NVCC_THREADS: 8
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheel-python${{ matrix.python-version }}-cuda${{ matrix.cuda-version }}${{ matrix.arch == 'aarch64' && '-aarch64' || '' }}
+          path: sgl-kernel/dist/*
+
+  release-cu130:
+    needs: build-cu130-matrix
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}
+
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-*
+
+      - name: Set tag name
+        id: set_tag_name
+        run: |
+          if [ -z "${{ inputs.tag_name }}" ]; then
+            TAG_NAME="v$(cat sgl-kernel/python/sgl_kernel/version.py | cut -d'"' -f2)"
+            echo "tag_name=$TAG_NAME" >> $GITHUB_OUTPUT
+          else
+            echo "tag_name=${{ inputs.tag_name }}" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Release
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: ${{ steps.set_tag_name.outputs.tag_name }}
+          repository: sgl-project/whl
+          token: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
+          files: |
+            sgl-kernel/dist/*
+
+      - name: Clone wheel index
+        run: git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl
+        env:
+          WHL_TOKEN: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
+
+      - name: Update wheel index
+        run: python3 scripts/update_kernel_whl_index.py --cuda 130
+
+      - name: Push wheel index
+        run: |
+          cd sgl-whl
+          git config --local user.name "sglang-bot"
+          git config --local user.email "sglangbot@gmail.com"
+          git add -A
+          git commit -m "update whl index"
+          git push
+
+  build-rocm-matrix:
+    if: |
+      github.repository == 'sgl-project/sglang' &&
+      (github.event_name == 'push' || github.event.inputs.target == 'all' || github.event.inputs.target == 'rocm700' || github.event.inputs.target == 'rocm720')
+    runs-on: amd-docker-scale
+    strategy:
+      matrix:
+        python-version: ["3.10"]
+        rocm-version: ["700", "720"]
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Build wheels
+        run: |
+          cp 3rdparty/amd/wheel/sgl-kernel/* sgl-kernel/
+          cd sgl-kernel
+          chmod +x ./build_rocm.sh
+          ./build_rocm.sh "${{ matrix.rocm-version }}"
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheel-python${{ matrix.python-version }}-rocm${{ matrix.rocm-version }}
+          path: sgl-kernel/dist/*
+
+  release-rocm700:
+    needs: build-rocm-matrix
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}
+
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-*-rocm700
+
+      - name: Set tag name
+        id: set_tag_name
+        run: |
+          if [ -z "${{ inputs.tag_name }}" ]; then
+            TAG_NAME="v$(cat sgl-kernel/python/sgl_kernel/version.py | cut -d'"' -f2)"
+            echo "tag_name=$TAG_NAME" >> $GITHUB_OUTPUT
+          else
+            echo "tag_name=${{ inputs.tag_name }}" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Release
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: ${{ steps.set_tag_name.outputs.tag_name }}
+          repository: sgl-project/whl
+          token: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
+          files: |
+            sgl-kernel/dist/*
+
+      - name: Clone wheel index
+        run: git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl
+        env:
+          WHL_TOKEN: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
+
+      - name: Update wheel index
+        run: python3 scripts/update_kernel_whl_index.py --rocm 700
+
+      - name: Push wheel index
+        run: |
+          cd sgl-whl
+          git config --local user.name "sglang-bot"
+          git config --local user.email "sglangbot@gmail.com"
+          git add -A
+          git commit -m "update whl index"
+          git push
+
+  release-rocm720:
+    needs: build-rocm-matrix
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}
+
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-*-rocm720
+
+      - name: Set tag name
+        id: set_tag_name
+        run: |
+          if [ -z "${{ inputs.tag_name }}" ]; then
+            TAG_NAME="v$(cat sgl-kernel/python/sgl_kernel/version.py | cut -d'"' -f2)"
+            echo "tag_name=$TAG_NAME" >> $GITHUB_OUTPUT
+          else
+            echo "tag_name=${{ inputs.tag_name }}" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Release
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: ${{ steps.set_tag_name.outputs.tag_name }}
+          repository: sgl-project/whl
+          token: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
+          files: |
+            sgl-kernel/dist/*
+
+      - name: Clone wheel index
+        run: git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl
+        env:
+          WHL_TOKEN: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
+
+      - name: Update wheel index
+        run: python3 scripts/update_kernel_whl_index.py --rocm 720
+
+      - name: Push wheel index
+        run: |
+          cd sgl-whl
+          git config --local user.name "sglang-bot"
+          git config --local user.email "sglangbot@gmail.com"
+          git add -A
+          git commit -m "update whl index"
+          git push
+
+  build-musa43:
+    if: |
+      github.repository == 'sgl-project/sglang' &&
+      (github.event_name == 'push' || github.event.inputs.target == 'all' || github.event.inputs.target == 'musa43')
+    runs-on: kernel-build-node-musa
+    strategy:
+      matrix:
+        python-version: ["3.10"]
+        musa-version: ["43"]
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+
+      - name: Build wheels
+        run: |
+          cd sgl-kernel
+          mv pyproject_musa.toml pyproject.toml
+          python setup_musa.py sdist bdist_wheel
+
+      - name: Rename MUSA wheels
+        run: |
+          bash scripts/ci/musa/rename_wheels_musa.sh ${{ matrix.musa-version }} sgl-kernel/dist
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheel-python${{ matrix.python-version }}-musa${{ matrix.musa-version }}
+          path: sgl-kernel/dist/*
+
+  release-musa43:
+    needs: build-musa43
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-*
+
+      - name: Set tag name
+        id: set_tag_name
+        run: |
+          if [ -z "${{ inputs.tag_name }}" ]; then
+            TAG_NAME="v$(cat sgl-kernel/python/sgl_kernel/version.py | cut -d'"' -f2)"
+            echo "tag_name=$TAG_NAME" >> $GITHUB_OUTPUT
+          else
+            echo "tag_name=${{ inputs.tag_name }}" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Release
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: ${{ steps.set_tag_name.outputs.tag_name }}
+          repository: sgl-project/whl
+          token: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
+          files: |
+            sgl-kernel/dist/*
+
+      - name: Clone wheel index
+        run: git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl
+        env:
+          WHL_TOKEN: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
+
+      - name: Update wheel index
+        run: python3 scripts/update_kernel_whl_index.py --musa 43
+
+      - name: Push wheel index
+        run: |
+          cd sgl-whl
+          git config --local user.name "sglang-bot"
+          git config --local user.email "sglangbot@gmail.com"
+          git add -A
+          git commit -m "update whl index"
+          git push

third_party/sglang/.github/workflows/rerun-test.yml

@@ -0,0 +1,136 @@
+name: Rerun Test
+run-name: ${{ inputs.pr_head_sha && format('[rerun-test] {0} {1}', inputs.test_command, inputs.pr_head_sha) || format('[rerun-test] {0}', inputs.test_command) }}
+
+on:
+  workflow_dispatch:
+    inputs:
+      test_command:
+        description: "Test command(s) to run, one per line (e.g. 'registered/core/test_srt_endpoint.py TestSRTEndpoint.test_simple_decode')"
+        required: true
+        type: string
+      runner_label:
+        description: "Runner label"
+        required: true
+        type: choice
+        options:
+          - 1-gpu-h100
+          - 1-gpu-5090
+          - 2-gpu-h100
+          - 4-gpu-h100
+          - 4-gpu-a10
+          - 4-gpu-b200
+          - 8-gpu-h200
+          - 8-gpu-h20
+          - 8-gpu-b200
+          - ubuntu-latest
+      pr_head_sha:
+        description: "PR head SHA to checkout (for /rerun-test on fork PRs)"
+        required: false
+        type: string
+        default: ""
+      use_deepep:
+        description: "Use ci_install_deepep.sh instead of ci_install_dependency.sh"
+        required: false
+        type: string
+        default: "false"
+      is_cpu:
+        description: "Run as CPU-only test (uses ubuntu-latest with uv pip install)"
+        required: false
+        type: string
+        default: "false"
+
+env:
+  SGLANG_IS_IN_CI: true
+  SGLANG_CUDA_COREDUMP: "1"
+  SGLANG_JIT_DEEPGEMM_FAST_WARMUP: true
+
+permissions:
+  actions: write
+  contents: read
+  issues: read
+
+jobs:
+  rerun-test-cuda:
+    if: inputs.is_cpu != 'true'
+    runs-on: ${{ inputs.runner_label }}
+    timeout-minutes: 120
+    env:
+      RUNNER_LABELS: ${{ inputs.runner_label }}
+      SGLANG_CI_RDMA_ALL_DEVICES: ${{ inputs.runner_label == '8-gpu-h20' && 'mlx5_1,mlx5_2,mlx5_3,mlx5_4' || '' }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || github.sha }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          if [[ "${{ inputs.runner_label }}" == "1-gpu-5090" ]]; then
+            source /etc/profile.d/sglang-ci.sh
+          fi
+          if [[ "${{ inputs.use_deepep }}" == "true" ]]; then
+            bash scripts/ci/cuda/ci_install_deepep.sh
+          else
+            bash scripts/ci/cuda/ci_install_dependency.sh
+          fi
+
+      - name: Run test
+        timeout-minutes: 60
+        run: |
+          if [[ "${{ inputs.runner_label }}" == "1-gpu-5090" ]]; then
+            source /etc/profile.d/sglang-ci.sh
+          fi
+          cd test/
+          echo "${{ inputs.test_command }}" | while IFS= read -r cmd; do
+            [ -z "$cmd" ] && continue
+            echo ">>> Running: python3 $cmd"
+            python3 $cmd || exit 1
+          done
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+
+  rerun-test-cpu:
+    if: inputs.is_cpu == 'true'
+    runs-on: ubuntu-latest
+    timeout-minutes: 120
+    steps:
+      - name: Free disk space
+        run: |
+          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc
+          df -h
+
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || github.sha }}
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        env:
+          UV_SYSTEM_PYTHON: "1"
+        run: |
+          uv pip install -e "python[dev]" --index-strategy unsafe-best-match --prerelease allow
+
+      - name: Run test
+        timeout-minutes: 60
+        run: |
+          cd test/
+          echo "${{ inputs.test_command }}" | while IFS= read -r cmd; do
+            [ -z "$cmd" ] && continue
+            echo ">>> Running: python3 $cmd"
+            python3 $cmd || exit 1
+          done

third_party/sglang/.github/workflows/retag-docker.yml

@@ -0,0 +1,30 @@
+name: Retag Docker Image
+
+on:
+  workflow_dispatch:
+    inputs:
+      source_tag:
+        description: "Existing image tag (e.g., v0.4.7-cu129-amd64)"
+        required: true
+      target_tag:
+        description: "New tag to apply (e.g., latest)"
+        required: true
+
+jobs:
+  retag:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: ubuntu-22.04
+    environment: "prod"
+    steps:
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Retag image
+        run: |
+          echo "Retagging lmsysorg/sglang:${{ inputs.source_tag }} -> lmsysorg/sglang:${{ inputs.target_tag }}"
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:${{ inputs.target_tag }} \
+            lmsysorg/sglang:${{ inputs.source_tag }}

third_party/sglang/.github/workflows/runner-utilization.yml

@@ -0,0 +1,43 @@
+name: Runner Utilization Report
+
+on:
+  schedule:
+    - cron: '0 8 * * *'  # Daily at 8 AM UTC
+  pull_request:
+    paths:
+      - '.github/workflows/runner-utilization.yml'
+      - 'scripts/ci/utils/runner_utilization_report.py'
+  workflow_dispatch:
+    inputs:
+      hours:
+        description: 'Time window in hours'
+        required: false
+        default: '24'
+        type: string
+      filter:
+        description: 'Filter runner labels (e.g., 5090, h200)'
+        required: false
+        type: string
+
+jobs:
+  report:
+    name: Generate Report
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Generate Utilization Report
+        timeout-minutes: 30
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          python scripts/ci/utils/runner_utilization_report.py \
+            --repo ${{ github.repository }} \
+            --hours ${{ inputs.hours || '24' }} \
+            ${{ inputs.filter && format('--filter {0}', inputs.filter) || '' }}

third_party/sglang/.github/workflows/slash-command-handler.yml

@@ -0,0 +1,99 @@
+name: Slash Command Handler
+
+on:
+  issue_comment:
+    types: [created, edited]
+
+permissions:
+  contents: read
+  pull-requests: write # Required to add labels and reactions
+  actions: write       # Required to rerun workflows
+  issues: write        # Required for comment reactions in some contexts
+
+jobs:
+  slash_command:
+    # Only run if it is a PR and the comment contains a recognized command
+    # Use contains() since startsWith() can't handle leading whitespace/newlines
+    if: >
+      github.event.issue.pull_request &&
+      (contains(github.event.comment.body, '/tag-run-ci-label') ||
+       contains(github.event.comment.body, '/rerun-failed-ci') ||
+       contains(github.event.comment.body, '/tag-and-rerun-ci') ||
+       contains(github.event.comment.body, '/rerun-stage') ||
+       contains(github.event.comment.body, '/rerun-test'))
+    runs-on: ubuntu-latest
+
+    steps:
+      # SECURITY: This workflow runs on issue_comment trigger with elevated permissions
+      # (pull-requests: write, actions: write). For non-fork PRs, we can safely checkout
+      # the PR branch to allow testing changes to this handler. For fork PRs, we MUST
+      # stay on main to prevent untrusted code execution with these elevated permissions.
+      - name: Get PR details
+        id: pr
+        shell: bash
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          PR_DATA=$(gh pr view ${{ github.event.issue.number }} --repo ${{ github.repository }} --json headRefName,headRepositoryOwner) || {
+            echo "::error::Failed to fetch PR data"
+            exit 1
+          }
+          # Use 'empty' filter to handle null/missing values (e.g., deleted forks)
+          HEAD_OWNER=$(echo "$PR_DATA" | jq -r '.headRepositoryOwner.login // empty')
+          REPO_OWNER="${{ github.repository_owner }}"
+          # Treat missing/null owner as fork for security (fail-safe)
+          if [[ -z "$HEAD_OWNER" || "$HEAD_OWNER" != "$REPO_OWNER" ]]; then
+            IS_FORK="true"
+          else
+            IS_FORK="false"
+          fi
+          echo "is_fork=$IS_FORK" >> $GITHUB_OUTPUT
+          echo "ref=$(echo "$PR_DATA" | jq -r '.headRefName')" >> $GITHUB_OUTPUT
+          echo "pr_ref=refs/pull/${{ github.event.issue.number }}/head" >> $GITHUB_OUTPUT
+          echo "PR owner: $HEAD_OWNER, Repo owner: $REPO_OWNER, Is fork: $IS_FORK"
+
+      - name: Check commenter permission for fork PRs
+        id: perm
+        if: steps.pr.outputs.is_fork == 'true'
+        shell: bash
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          PERM=$(gh api repos/${{ github.repository }}/collaborators/${{ github.event.comment.user.login }}/permission --jq '.permission') || {
+            PERM="none"
+            echo "::warning::Failed to check commenter permission, defaulting to none"
+          }
+          if [[ "$PERM" == "admin" || "$PERM" == "maintain" || "$PERM" == "write" ]]; then
+            echo "safe_to_checkout_pr=true" >> $GITHUB_OUTPUT
+          else
+            echo "safe_to_checkout_pr=false" >> $GITHUB_OUTPUT
+          fi
+          echo "Commenter ${{ github.event.comment.user.login }} permission: $PERM"
+
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          # For non-fork PRs: checkout PR branch by name
+          # For fork PRs with trusted commenter: checkout via refs/pull/N/head
+          # For fork PRs with untrusted commenter: stay on main for security
+          ref: ${{ steps.pr.outputs.is_fork == 'false' && steps.pr.outputs.ref || (steps.perm.outputs.safe_to_checkout_pr == 'true' && steps.pr.outputs.pr_ref || '') }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: |
+          pip install PyGithub
+
+      - name: Handle Slash Command
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          REPO_FULL_NAME: ${{ github.repository }}
+          PR_NUMBER: ${{ github.event.issue.number }}
+          COMMENT_ID: ${{ github.event.comment.id }}
+          COMMENT_BODY: ${{ github.event.comment.body }}
+          USER_LOGIN: ${{ github.event.comment.user.login }}
+        run: |
+          python scripts/ci/utils/slash_command_handler.py

third_party/sglang/.github/workflows/stress-test.yml

@@ -0,0 +1,44 @@
+name: Stress Test
+
+on:
+  workflow_dispatch:
+    inputs:
+      num_prompts:
+        description: 'Number of prompts per model'
+        required: true
+        default: '50000'
+        type: string
+      duration_minutes:
+        description: 'Timeout per model in minutes'
+        required: true
+        default: '45'
+        type: string
+
+jobs:
+  stress-test:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: 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 stress tests
+        timeout-minutes: 210
+        env:
+          NUM_PROMPTS: ${{ inputs.num_prompts }}
+          DURATION_MINUTES: ${{ inputs.duration_minutes }}
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite stress
+
+      - name: Upload results
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: stress-test-results
+          path: |
+            stress_test_*.jsonl

third_party/sglang/.github/workflows/trivy-scan-dev.yml

@@ -0,0 +1,85 @@
+name: Trivy Scan Dev Docker Images
+
+on:
+  # Run daily after nightly dev builds (which run at midnight UTC)
+  schedule:
+    - cron: "0 6 * * *"
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: "Image tag to scan (e.g., dev, dev-cu13, latest)"
+        required: false
+        default: ""
+
+jobs:
+  scan:
+    if: github.repository == 'sgl-project/sglang'
+    runs-on: x64-docker-build-node
+    timeout-minutes: 45
+    permissions:
+      contents: read
+      security-events: write
+    strategy:
+      fail-fast: false
+      matrix:
+        tag: ${{ inputs.tag && fromJSON(format('["{0}"]', inputs.tag)) || fromJSON('["dev", "dev-cu13"]') }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Run Trivy vulnerability scanner
+        uses: aquasecurity/trivy-action@v0.35.0
+        with:
+          image-ref: 'docker.io/lmsysorg/sglang:${{ matrix.tag }}'
+          scanners: 'vuln'
+          format: 'sarif'
+          output: 'trivy-results-${{ matrix.tag }}.sarif'
+          severity: 'CRITICAL,HIGH'
+          ignore-unfixed: true
+          skip-dirs: 'usr/local/go,opt/nvidia'
+
+      - name: Upload Trivy scan results to GitHub Security
+        uses: github/codeql-action/upload-sarif@v4
+        if: always() && hashFiles(format('trivy-results-{0}.sarif', matrix.tag)) != ''
+        with:
+          sarif_file: 'trivy-results-${{ matrix.tag }}.sarif'
+          category: 'trivy-${{ matrix.tag }}'
+
+      - name: Run Trivy (table output for logs)
+        if: success()
+        uses: aquasecurity/trivy-action@v0.35.0
+        with:
+          image-ref: 'docker.io/lmsysorg/sglang:${{ matrix.tag }}'
+          scanners: 'vuln'
+          format: 'table'
+          severity: 'CRITICAL,HIGH'
+          ignore-unfixed: true
+          skip-dirs: 'usr/local/go,opt/nvidia'
+
+      - name: Scan summary
+        if: always()
+        run: |
+          IMAGE="docker.io/lmsysorg/sglang:${{ matrix.tag }}"
+          SARIF="trivy-results-${{ matrix.tag }}.sarif"
+
+          echo "## Trivy Scan: \`${{ matrix.tag }}\`" >> "$GITHUB_STEP_SUMMARY"
+
+          if [ ! -f "${SARIF}" ]; then
+            echo "**Status:** Scan failed — no SARIF output produced" >> "$GITHUB_STEP_SUMMARY"
+            exit 0
+          fi
+
+          VULN_COUNT=$(python3 -c "
+          import json
+          data = json.load(open('${SARIF}'))
+          print(sum(len(run.get('results', [])) for run in data.get('runs', [])))
+          ")
+
+          echo "- **Image**: \`${IMAGE}\`" >> "$GITHUB_STEP_SUMMARY"
+          echo "- **Findings**: ${VULN_COUNT}" >> "$GITHUB_STEP_SUMMARY"
+
+          if [ "${VULN_COUNT}" = "0" ]; then
+            echo "- **Result**: No CRITICAL/HIGH unfixed vulnerabilities found" >> "$GITHUB_STEP_SUMMARY"
+          else
+            echo "- **Result**: Found ${VULN_COUNT} finding(s) — check the Security tab for details" >> "$GITHUB_STEP_SUMMARY"
+          fi

third_party/sglang/.github/workflows/weekly-test-nvidia.yml

@@ -0,0 +1,49 @@
+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
+  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