fix: update run_suite (#10685)

.github/workflows/pr-test.yml

@@ -591,11 +591,11 @@ jobs:
           cd test/srt
           python3 run_suite.py --suite per-commit-8-gpu-deepep
 
-  unit-test-backend-8-gpu-b200:
+  unit-test-backend-4-gpu-b200:
     needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels]
     if: always() && !failure() && !cancelled() &&
         ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
-    runs-on: b200-runner
+    runs-on: 4-b200-runner
     strategy:
       fail-fast: false
     steps:
@@ -618,7 +618,7 @@ jobs:
         timeout-minutes: 60
         run: |
           cd test/srt
-          python3 run_suite.py --suite per-commit-8-gpu-b200 --auto-partition-id 0 --auto-partition-size 1
+          python3 run_suite.py --suite per-commit-4-gpu-b200 --auto-partition-id 0 --auto-partition-size 1
 
   pr-test-finish:
     needs: [
@@ -632,7 +632,7 @@ jobs:
       performance-test-1-gpu-part-1, performance-test-1-gpu-part-2, performance-test-2-gpu,
       accuracy-test-1-gpu, accuracy-test-2-gpu,
       unit-test-deepep-4-gpu, unit-test-deepep-8-gpu,
-      unit-test-backend-8-gpu-b200,
+      unit-test-backend-4-gpu-b200,
     ]
     if: always()
     runs-on: ubuntu-latest

test/srt/run_suite.py

@@ -150,7 +150,7 @@ suites = {
         TestFile("test_disaggregation_pp.py", 60),
         TestFile("test_full_deepseek_v3.py", 333),
     ],
-    "per-commit-8-gpu-b200": [
+    "per-commit-4-gpu-b200": [
         TestFile("test_gpt_oss_4gpu.py", 600),
         TestFile("test_deepseek_v3_fp4_4gpu.py", 600),
     ],