Create cancel-all-pr-test-runs (#8986)

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

@@ -0,0 +1,32 @@
+name: Cancel All Pending PR Test Runs
+
+on:
+  workflow_dispatch: # Manual trigger
+
+jobs:
+  cancel-pending:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Install GitHub CLI
+        run: apt-get install -y gh jq
+
+      - name: Authenticate GitHub CLI
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: gh auth login --with-token <<< "$GH_TOKEN"
+
+      - name: Cancel all pending/waiting pr-test.yml runs
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          REPO: ${{ github.repository }}
+        run: |
+          # Get all pending or waiting runs of pr-test.yml across all branches
+          gh run list \
+            --workflow pr-test.yml \
+            --json databaseId,status,conclusion \
+            --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"
+              done

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

@@ -323,7 +323,7 @@ jobs:
           docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_moe_topk_softmax.py
           docker exec -w /sglang-checkout/sgl-kernel/tests/speculative ci_sglang python3 -m pytest test_eagle_utils.py
 
-  finish:
+  pr-test-amd-finish:
     if: always()
     needs: [
       accuracy-test-1-gpu-amd, mla-test-1-gpu-amd, bench-test-2-gpu-amd,

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

@@ -109,7 +109,7 @@ jobs:
           cd test/srt
           python3 run_suite.py --suite per-commit-4-ascend-npu --timeout-per-file 3600
 
-  finish:
+  pr-test-npu-finish:
     if: always()
     needs:
       - per-commit-1-ascend-npu

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

@@ -1,17 +1,32 @@
 name: PR Test (Xeon)
+
 on:
+  push:
+    branches: [ main ]
+    paths:
+      - "python/**"
+      - "scripts/**"
+      - "test/**"
+      - "sgl-kernel/**"
+      - ".github/workflows/pr-test-xeon.yml"
   pull_request:
-    branches:
+    branches: [ main ]
-      - main
+    paths:
+      - "python/**"
+      - "scripts/**"
+      - "test/**"
+      - "sgl-kernel/**"
+      - ".github/workflows/pr-test-xeon.yml"
   workflow_dispatch:
 
 concurrency:
-  group: pr-test-xeon
+  group: pr-test-xeon-${{ github.ref }}
   cancel-in-progress: false
 
 jobs:
   build-test:
-    if: github.event_name == 'pull_request'
+    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
+      github.event.pull_request.draft == false
     runs-on: sglang-pvc
     strategy:
       matrix:
@@ -34,16 +49,15 @@ jobs:
             --name ci_sglang_xeon \
             sglang_xeon
 
-      - name: Install Dependency
+      - name: Install dependencies
         timeout-minutes: 20
         run: |
           docker exec ci_sglang_xeon bash -c "python3 -m pip install --upgrade pip"
           docker exec ci_sglang_xeon pip uninstall sgl-kernel -y || true
           docker exec -w /sglang-checkout/sgl-kernel ci_sglang_xeon bash -c "cp pyproject_cpu.toml pyproject.toml && pip install -v ."
-          docker exec -w /sglang-checkout/ ci_sglang_xeon bash -c "pip install -e "python[all_cpu]""
+          docker exec -w /sglang-checkout/ ci_sglang_xeon bash -c "pip install -e "python[dev_cpu]""
-          docker exec ci_sglang_xeon bash -c "python3 -m pip install pytest expecttest"
 
-      - name: Check AMX Support
+      - name: Check AMX support
         id: check_amx
         timeout-minutes: 5
         run: |
@@ -51,7 +65,7 @@ jobs:
             bash -c "python3 -c 'import torch; import sgl_kernel; assert torch._C._cpu._is_amx_tile_supported(); assert hasattr(torch.ops.sgl_kernel, \"convert_weight_packed\"); '"
         continue-on-error: true
 
-      - name: Run UT Cases
+      - name: Run unit tests
         if: steps.check_amx.outcome == 'success'
         timeout-minutes: 20
         run: |
@@ -63,10 +77,10 @@ jobs:
         run: |
           docker rm -f ci_sglang_xeon || true
 
-  finish:
+  pr-test-xeon-finish:
     if: always()
     needs: [build-test]
-    runs-on: ubuntu-24.04
+    runs-on: ubuntu-latest
     steps:
       - name: Check all dependent job statuses
         run: |

python/pyproject.toml

@@ -105,6 +105,7 @@ torch_memory_saver = ["torch_memory_saver>=0.0.8"]
 decord = ["decord"]
 test = [
     "accelerate",
+    "expecttest",
     "jsonlines",
     "matplotlib",
     "pandas",