Run tests based on labels (#10456)

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

@@ -17,6 +17,7 @@ on:
       - "test/**"
       - "sgl-kernel/**"
       - ".github/workflows/pr-test-amd.yml"
+    types: [synchronize, labeled]
   workflow_dispatch:
 
 concurrency:
@@ -25,8 +26,7 @@ concurrency:
 
 jobs:
   accuracy-test-1-gpu-amd:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
-      github.event.pull_request.draft == false
+    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
     strategy:
       fail-fast: false
       matrix:
@@ -52,8 +52,7 @@ jobs:
           bash scripts/ci/amd_ci_exec.sh python3 models/test_qwen_models.py
 
   accuracy-test-2-gpu-amd:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
-        github.event.pull_request.draft == false
+    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
     strategy:
       fail-fast: false
       matrix:
@@ -77,8 +76,7 @@ jobs:
           bash scripts/ci/amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_moe_eval_accuracy_large.py
 
   mla-test-1-gpu-amd:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
-      github.event.pull_request.draft == false
+    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
     strategy:
       fail-fast: false
       matrix:
@@ -102,8 +100,7 @@ jobs:
           bash scripts/ci/amd_ci_exec.sh python3 test_mla.py
 
   performance-test-1-gpu-part-1-amd:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
-        github.event.pull_request.draft == false
+    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
     strategy:
       fail-fast: false
       matrix:
@@ -143,8 +140,7 @@ jobs:
           bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_non_stream_small_batch_size
 
   performance-test-1-gpu-part-2-amd:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
-        github.event.pull_request.draft == false
+    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
     strategy:
       fail-fast: false
       matrix:
@@ -178,8 +174,7 @@ jobs:
           bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default_fp8
 
   bench-test-2-gpu-amd:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
-      github.event.pull_request.draft == false
+    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
     strategy:
       fail-fast: false
       matrix:
@@ -223,8 +218,7 @@ jobs:
           bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_without_radix_cache
 
   unit-test-backend-1-gpu-amd:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
-      github.event.pull_request.draft == false
+    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
     strategy:
       fail-fast: false
       matrix:
@@ -249,8 +243,7 @@ jobs:
           bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 8
 
   unit-test-backend-1-gpu-amd-mi35x:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
-      github.event.pull_request.draft == false
+    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
     strategy:
       fail-fast: false
       matrix:
@@ -274,8 +267,7 @@ jobs:
           bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd-mi35x
 
   unit-test-backend-2-gpu-amd:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
-      github.event.pull_request.draft == false
+    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
     strategy:
       fail-fast: false
       matrix:
@@ -299,8 +291,7 @@ jobs:
           bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-2-gpu-amd
 
   unit-test-backend-8-gpu-amd:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
-      github.event.pull_request.draft == false
+    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
     strategy:
       fail-fast: false
       matrix:
@@ -324,8 +315,7 @@ jobs:
           bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-8-gpu-amd --timeout-per-file 3600
 
   unit-test-sgl-kernel-amd:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
-      github.event.pull_request.draft == false
+    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
     strategy:
       fail-fast: false
       matrix:
@@ -353,25 +343,3 @@ jobs:
           docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_apply_token_bitmask_inplace.py
           docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_activation.py
           docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_kvcacheio.py
-
-  pr-test-amd-finish:
-    if: always()
-    needs: [
-      accuracy-test-1-gpu-amd, mla-test-1-gpu-amd, bench-test-2-gpu-amd,
-      accuracy-test-2-gpu-amd, performance-test-1-gpu-part-1-amd, performance-test-1-gpu-part-2-amd,
-      unit-test-backend-1-gpu-amd, unit-test-backend-1-gpu-amd-mi35x, unit-test-backend-2-gpu-amd,
-      unit-test-backend-8-gpu-amd, unit-test-sgl-kernel-amd
-    ]
-    runs-on: ubuntu-latest
-    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