Merge branch 'main' into gpt_oss_cutlass

Author: Fridge003

.github/CODEOWNERS

@@ -1,8 +1,9 @@
-.github @merrymercy @zhyncs
-/docker @zhyncs @HaiShaw @ByronHsu
+.github @merrymercy @Fridge003 @ispobock
+/docker @Fridge003 @ispobock @HaiShaw @ByronHsu
 /docker/npu.Dockerfile @ping1jing2
-/python/pyproject.toml @merrymercy @zhyncs
-/python/sglang/* @merrymercy @Ying1123 @zhyncs @hnyls2002
+/python/pyproject.toml @merrymercy @Fridge003 @ispobock
+/python/sglang/* @merrymercy @Ying1123 @Fridge003 @ispobock @hnyls2002
+/python/sglang/multimodal_gen @mickqian
 /python/sglang/srt/constrained @hnyls2002
 /python/sglang/srt/disaggregation @ByronHsu @hnyls2002
 /python/sglang/srt/disaggregation/mooncake @ShangmingCai
@@ -11,14 +12,14 @@
 /python/sglang/srt/entrypoints @ispobock @CatherineSue @slin1237 @merrymercy @JustinTong0323
 /python/sglang/srt/eplb @fzyzcjy
 /python/sglang/srt/function_call @CatherineSue @JustinTong0323
-/python/sglang/srt/layers @merrymercy @Ying1123 @zhyncs @ispobock @HaiShaw @ch-wan @BBuf @kushanam @Edwardf0t1
+/python/sglang/srt/layers @merrymercy @Ying1123 @Fridge003 @ispobock @HaiShaw @ch-wan @BBuf @kushanam @Edwardf0t1
 /python/sglang/srt/layers/quantization @ch-wan @BBuf @Edwardf0t1 @FlamingoPg
 /python/sglang/srt/layers/attention/ascend_backend.py @ping1jing2
 /python/sglang/srt/lora @Ying1123 @Fridge003 @lifuhuang
-/python/sglang/srt/managers @merrymercy @Ying1123 @hnyls2002 @xiezhq-hermann
+/python/sglang/srt/managers @merrymercy @Ying1123 @zhyncs @hnyls2002 @xiezhq-hermann
 /python/sglang/srt/mem_cache @merrymercy @Ying1123 @hnyls2002 @xiezhq-hermann
 /python/sglang/srt/mem_cache/allocator_ascend.py @ping1jing2
-/python/sglang/srt/model_executor @merrymercy @Ying1123 @hnyls2002 @zhyncs @ispobock
+/python/sglang/srt/model_executor @merrymercy @Ying1123 @hnyls2002 @Fridge003 @ispobock
 /python/sglang/srt/model_executor/npu_graph_runner.py @ping1jing2
 /python/sglang/srt/multimodal @mickqian @JustinTong0323
 /python/sglang/srt/speculative @Ying1123 @merrymercy @kssteven418

.github/labeler.yml

@@ -2,18 +2,10 @@
 # Automatically adds labels to PRs based on the files changed
 
 # Router specific (Rust code in sgl-router)
-router:
+model-gateway:
   - changed-files:
     - any-glob-to-any-file: 'sgl-router/**/*'
 
-# Router benchmarks
-router-benchmark:
-  - changed-files:
-    - any-glob-to-any-file:
-      - 'sgl-router/benches/**/*'
-      - 'sgl-router/scripts/run_benchmarks.py'
-      - 'sgl-router/**/*bench*.rs'
-
 # Kernel specific
 sgl-kernel:
   - changed-files:
@@ -64,15 +56,6 @@ quant:
       - '**/awq/**/*'
       - '**/gptq/**/*'
 
-# Performance related
-performance:
-  - changed-files:
-    - any-glob-to-any-file:
-      - '**/benchmark/**/*'
-      - '**/benches/**/*'
-      - '**/perf/**/*'
-      - '**/*benchmark*'
-
 # Speculative decoding
 speculative-decoding:
   - changed-files:

.github/workflows/auto-format.yml

@@ -0,0 +1,71 @@
+name: Auto Format Code
+
+on:
+  pull_request:
+    types: [labeled]
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  auto-format:
+    if: github.event.label.name == 'format'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout PR branch
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.pull_request.head.ref }}
+          repository: ${{ github.event.pull_request.head.repo.full_name }}
+          token: ${{ secrets.GITHUB_TOKEN }}
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+
+      - name: Install pre-commit hook
+        run: |
+          python -m pip install pre-commit
+          pre-commit install
+
+      - name: Run pre-commit to format code
+        run: SKIP=no-commit-to-branch pre-commit run --all-files
+        continue-on-error: true
+
+      - name: Check for changes
+        id: check_changes
+        run: |
+          if [[ -n $(git status -s) ]]; then
+            echo "has_changes=true" >> $GITHUB_OUTPUT
+          else
+            echo "has_changes=false" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Commit and push changes
+        if: steps.check_changes.outputs.has_changes == 'true'
+        run: |
+          git config --local user.email "github-actions[bot]@users.noreply.github.com"
+          git config --local user.name "github-actions[bot]"
+          git add .
+          git commit -m "🤖 Auto-format code with isort, black, ruff, and clang-format"
+          git push
+
+      - name: Remove format label
+        if: always()
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            try {
+              await github.rest.issues.removeLabel({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: context.issue.number,
+                name: 'format'
+              });
+            } catch (error) {
+              console.log('Label may have already been removed');
+            }

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

@@ -0,0 +1,55 @@
+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
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install Python dependencies
+        run: |
+          pip install tomli
+
+      - name: Check if sync is needed
+        id: check_sync
+        run: |
+          python scripts/release/check_kernel_version_to_sglang.py
+
+      - name: Configure Git and branch
+        if: steps.check_sync.outputs.needs_sync == 'true'
+        run: |
+          git config user.name "sglang-bot"
+          git config user.email "[email protected]"
+          RANDOM_SUFFIX=$(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
+
+      - 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"

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

@@ -0,0 +1,64 @@
+name: CI Failure Monitor
+
+on:
+  schedule:
+    - cron: '*/30 * * * *' # Every 30 minutes
+  workflow_dispatch:
+    inputs:
+      limit:
+        description: 'Number of workflow runs to analyze'
+        required: false
+        default: '300'
+        type: string
+      threshold:
+        description: 'Alert threshold for consecutive failures'
+        required: false
+        default: '4'
+        type: string
+
+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
+
+      - name: Run Failure Analysis
+        env:
+          GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
+          PYTHONUNBUFFERED: 1
+          PYTHONIOENCODING: utf-8
+        run: |
+          cd scripts/ci_monitor
+          python ci_failures_analysis.py \
+            --token $GITHUB_TOKEN \
+            --limit ${{ inputs.limit || '300' }} \
+            --threshold ${{ inputs.threshold || '2' }} \
+            --output ci_failure_analysis_$(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

.github/workflows/label-pr.yml

@@ -12,8 +12,34 @@ jobs:
   label:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/labeler@v5
+      # Step 1: Add category labels based on file changes
+      - name: Auto-label by file changes
+        uses: actions/labeler@v5
         with:
           repo-token: "${{ secrets.GITHUB_TOKEN }}"
           configuration-path: .github/labeler.yml
           sync-labels: false
+
+      # Step 2: Add run-ci label for authorized users (only on opened/reopened)
+      - name: Check user permission
+        if: github.event.action == 'opened' || github.event.action == 'reopened'
+        id: checkAccess
+        uses: actions-cool/check-user-permission@v2
+        with:
+          require: write
+          username: ${{ github.triggering_actor }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Add run-ci label
+        if: (github.event.action == 'opened' || github.event.action == 'reopened') && steps.checkAccess.outputs.require-result == 'true'
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GH_PAT_FOR_PULL_REQUEST }}
+          script: |
+            github.rest.issues.addLabels({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: context.issue.number,
+              labels: ['run-ci']
+            })