Fix CI (#9013)

.github/workflows/cancel-all-pending-pr-test-runs.yml

@@ -2,6 +2,12 @@ name: Cancel All Pending PR Test Runs
 
 on:
   workflow_dispatch:
+    inputs:
+      workflows:
+        description: 'Space-separated list of workflow filenames to cancel'
+        required: true
+        type: string
+        default: 'pr-test.yml pr-test-xeon.yml'
 
 permissions:
   actions: write   # Needed to cancel runs
@@ -14,18 +20,26 @@ jobs:
       - name: Install GitHub CLI
         run: sudo apt-get install -y gh jq
 
-      - name: Cancel all pending/waiting pr-test.yml runs
+      - name: Cancel all pending/waiting runs for specified workflows
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           REPO: ${{ github.repository }}
         run: |
-          gh run list \
-            --repo "$REPO" \
-            --workflow pr-test.yml \
-            --json databaseId,status \
-            --limit 1000 \
-            | jq -r '.[] | select(.status=="queued" or .status=="in_progress") | .databaseId' \
-            | while read run_id; do
-                echo "Cancelling run ID: $run_id"
-                gh run cancel "$run_id" --repo "$REPO"
-              done
+          # Read the space-separated string from the input into a bash array
+          WORKFLOW_FILES=(${{ github.event.inputs.workflows }})
+
+          echo "Targeting ${#WORKFLOW_FILES[@]} workflow(s): ${{ github.event.inputs.workflows }}"
+
+          for workflow_file in "${WORKFLOW_FILES[@]}"; do
+            echo "--- Checking workflow: $workflow_file ---"
+            gh run list \
+              --repo "$REPO" \
+              --workflow "$workflow_file" \
+              --json databaseId,status \
+              --limit 1000 \
+              | jq -r '.[] | select(.status=="queued" or .status=="in_progress") | .databaseId' \
+              | while read run_id; do
+                  echo "Cancelling run ID: $run_id for workflow: $workflow_file"
+                  gh run cancel "$run_id" --repo "$REPO"
+                done
+          done

.github/workflows/execute-notebook.yml

@@ -41,7 +41,7 @@ jobs:
           make compile
 
 
-  finish:
+  notebook-finish:
     needs: [
       run-all-notebooks
     ]

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

@@ -27,7 +27,7 @@ jobs:
   build-test:
     if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
       github.event.pull_request.draft == false
-    runs-on: sglang-gnr
+    runs-on: xeon-pvc
     strategy:
       matrix:
         build_type: ['all']

.github/workflows/pr-test.yml

@@ -85,7 +85,7 @@ jobs:
           python3 run_suite.py --suite per-commit --auto-partition-id ${{ matrix.part }} --auto-partition-size 10
 
   unit-test-backend-2-gpu:
-    needs: [check-changes, unit-test-frontend]
+    needs: [check-changes]
     if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
         github.event.pull_request.draft == false &&
         needs.check-changes.outputs.src == 'true'
@@ -110,6 +110,10 @@ jobs:
         github.event.pull_request.draft == false &&
         needs.check-changes.outputs.src == 'true'
     runs-on: 4-gpu-runner
+    strategy:
+      fail-fast: false
+      matrix:
+        part: [0, 1]
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -119,10 +123,10 @@ jobs:
           bash scripts/ci_install_dependency.sh
 
       - name: Run test
-        timeout-minutes: 30
+        timeout-minutes: 20
         run: |
           cd test/srt
-          python3 run_suite.py --suite per-commit-4-gpu
+          python3 run_suite.py --suite per-commit-4-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
 
   unit-test-backend-8-gpu:
     needs: [check-changes, unit-test-backend-2-gpu]