Merge branch 'main' into amd-ci-monitor

Author: bingxche

.codespellrc

@@ -0,0 +1,3 @@
+[codespell]
+ignore-words-list = ans, als, hel, boostrap, childs, te, vas, hsa, ment, cann, thi, makro, wil, rouge, PRIS
+skip = *.json,*.jsonl,*.patch,*.txt

.github/CI_PERMISSIONS.json

@@ -209,6 +209,13 @@
         "reason": "top contributor",
         "can_rerun_stage": true
     },
+    "Shunkangz": {
+        "can_tag_run_ci_label": true,
+        "can_rerun_failed_ci": true,
+        "cooldown_interval_minutes": 60,
+        "reason": "custom override",
+        "can_rerun_stage": true
+    },
     "SimonCqk": {
         "can_tag_run_ci_label": true,
         "can_rerun_failed_ci": true,
@@ -279,6 +286,13 @@
         "reason": "custom override",
         "can_rerun_stage": true
     },
+    "ZhengWG": {
+        "can_tag_run_ci_label": true,
+        "can_rerun_failed_ci": true,
+        "cooldown_interval_minutes": 60,
+        "reason": "custom override",
+        "can_rerun_stage": true
+    },
     "ZhengdQin": {
         "can_tag_run_ci_label": true,
         "can_rerun_failed_ci": true,
@@ -405,6 +419,13 @@
         "reason": "custom override",
         "can_rerun_stage": true
     },
+    "dongjiyingdjy": {
+        "can_tag_run_ci_label": true,
+        "can_rerun_failed_ci": true,
+        "cooldown_interval_minutes": 60,
+        "reason": "custom override",
+        "can_rerun_stage": true
+    },
     "dougyster": {
         "can_tag_run_ci_label": true,
         "can_rerun_failed_ci": true,
@@ -660,7 +681,7 @@
     "liusy58": {
         "can_tag_run_ci_label": true,
         "can_rerun_failed_ci": true,
-        "cooldown_interval_minutes": 60,
+        "cooldown_interval_minutes": 0,
         "reason": "custom override",
         "can_rerun_stage": true
     },
@@ -804,6 +825,13 @@
         "reason": "top contributor",
         "can_rerun_stage": true
     },
+    "samuellees": {
+        "can_tag_run_ci_label": true,
+        "can_rerun_failed_ci": true,
+        "cooldown_interval_minutes": 60,
+        "reason": "custom override",
+        "can_rerun_stage": true
+    },
     "scottjlee": {
         "can_tag_run_ci_label": true,
         "can_rerun_failed_ci": true,
@@ -958,6 +986,13 @@
         "reason": "custom override",
         "can_rerun_stage": true
     },
+    "xyjixyjixyji": {
+        "can_tag_run_ci_label": true,
+        "can_rerun_failed_ci": true,
+        "cooldown_interval_minutes": 0,
+        "reason": "custom override",
+        "can_rerun_stage": true
+    },
     "yanbing-j": {
         "can_tag_run_ci_label": true,
         "can_rerun_failed_ci": true,
@@ -972,6 +1007,13 @@
         "reason": "custom override",
         "can_rerun_stage": true
     },
+    "yeahdongcn": {
+        "can_tag_run_ci_label": true,
+        "can_rerun_failed_ci": true,
+        "cooldown_interval_minutes": 0,
+        "reason": "custom override",
+        "can_rerun_stage": true
+    },
     "yhyang201": {
         "can_tag_run_ci_label": true,
         "can_rerun_failed_ci": true,

.github/CODEOWNERS

@@ -3,9 +3,10 @@
 /docker/npu.Dockerfile @ping1jing2 @iforgetmyname
 /python/pyproject.toml @merrymercy @Fridge003 @ispobock
 /python/sglang/jit_kernel @DarkSharpness @BBuf
+/python/sglang/jit_kernel/diffusion @yingluosanqian @BBuf @mickqian
 /python/sglang/multimodal_gen @mickqian @yhyang201
-/python/sglang/multimodal_gen/runtime/layers @mickqian @yhyang201 @BBuf
-/python/sglang/multimodal_gen/runtime/models/dits @mickqian @yhyang201 @BBuf
+/python/sglang/multimodal_gen/runtime/layers @mickqian @yhyang201 @BBuf @yingluosanqian
+/python/sglang/multimodal_gen/runtime/models/dits @mickqian @yhyang201 @BBuf @yingluosanqian
 /python/sglang/srt/batch_invariant_ops @Fridge003 @hebiao064
 /python/sglang/srt/constrained @hnyls2002 @DarkSharpness
 /python/sglang/srt/compilation @hebiao064

.github/labeler.yml

@@ -108,3 +108,10 @@ deterministic:
 piecewise-cuda-graph:
   - changed-files:
     - any-glob-to-any-file: 'python/sglang/srt/compilation/**/*'
+
+# Moore Threads specific
+mthreads:
+  - changed-files:
+    - any-glob-to-any-file:
+      - '**/*mthreads*'
+      - '**/*musa*'

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

@@ -6,7 +6,7 @@ on:
   pull_request:
     paths:
       - '.github/workflows/ci-coverage-overview.yml'
-      - 'scripts/ci/ci_coverage_report.py'
+      - 'scripts/ci/utils/ci_coverage_report.py'
       - 'test/registered/**'
   workflow_dispatch:
     inputs:
@@ -34,7 +34,7 @@ jobs:
 
       - name: Generate Summary Report
         run: |
-          python scripts/ci/ci_coverage_report.py --section summary
+          python scripts/ci/utils/ci_coverage_report.py --section summary
 
   by-folder:
     name: Tests by Folder
@@ -50,7 +50,7 @@ jobs:
 
       - name: Generate Tests by Folder Report
         run: |
-          python scripts/ci/ci_coverage_report.py --section by-folder
+          python scripts/ci/utils/ci_coverage_report.py --section by-folder
 
   by-suite:
     name: Tests by Suite
@@ -66,7 +66,7 @@ jobs:
 
       - name: Generate Tests by Suite Report
         run: |
-          python scripts/ci/ci_coverage_report.py --section by-suite
+          python scripts/ci/utils/ci_coverage_report.py --section by-suite
 
   json-export:
     name: JSON Export
@@ -83,7 +83,7 @@ jobs:
 
       - name: Generate JSON Report
         run: |
-          python scripts/ci/ci_coverage_report.py --output-format json > ci_coverage.json
+          python scripts/ci/utils/ci_coverage_report.py --output-format json > ci_coverage.json
 
       - name: Upload JSON artifact
         uses: actions/upload-artifact@v4

.github/workflows/execute-notebook.yml

@@ -3,28 +3,40 @@ 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-runner
-    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
+    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/ci_install_dependency.sh
+          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
@@ -43,9 +55,11 @@ jobs:
 
   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: |