[CI] Tiny refactoring sgl-kernel tests (#13813)

.github/workflows/pr-test.yml

@@ -256,36 +256,37 @@ jobs:
 
           echo "All benchmark tests completed!"
 
-  sgl-kernel-b200-test:
+  # sgl-kernel-b200-test:
-    needs: [check-changes, sgl-kernel-build-wheels]
+  #   needs: [check-changes, sgl-kernel-build-wheels]
-    if: needs.check-changes.outputs.sgl_kernel == 'true'
+  #   if: needs.check-changes.outputs.sgl_kernel == 'true'
-    runs-on: 4-gpu-b200
+  #   runs-on: 4-gpu-b200
-    env:
+  #   env:
-      RUNNER_LABELS: 4-gpu-b200
+  #     RUNNER_LABELS: 4-gpu-b200
-    steps:
+  #   steps:
-      - uses: actions/checkout@v4
+  #     - uses: actions/checkout@v4
 
-      - name: Cleanup
+  #     - name: Cleanup
-        run: |
+  #       run: |
-          ls -alh sgl-kernel/dist || true
+  #         ls -alh sgl-kernel/dist || true
-          rm -rf sgl-kernel/dist/* || true
+  #         rm -rf sgl-kernel/dist/* || true
 
-      - name: Download artifacts
+  #     - name: Download artifacts
-        uses: actions/download-artifact@v4
+  #       uses: actions/download-artifact@v4
-        with:
+  #       with:
-          path: sgl-kernel/dist/
+  #         path: sgl-kernel/dist/
-          merge-multiple: true
+  #         merge-multiple: true
-          pattern: wheel-python3.10-cuda12.9
+  #         pattern: wheel-python3.10-cuda12.9
 
-      - name: Install dependencies
+  #     - name: Install dependencies
-        run: |
+  #       run: |
-          CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 bash scripts/ci/ci_install_dependency.sh
+  #         CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 bash scripts/ci/ci_install_dependency.sh
+
+  #     - name: Run sgl-kernel unit tests on B200
+  #       timeout-minutes: 30
+  #       run: |
+  #         cd sgl-kernel
+  #         pytest tests/
 
-      - name: Run sgl-kernel unit tests on B200
-        timeout-minutes: 30
-        run: |
-          cd sgl-kernel
-          pytest tests/
   # Adding a single CUDA13 smoke test to verify that the kernel builds and runs
   # TODO: Add back this test when it can pass on CI
   # cuda13-kernel-smoke-test:
@@ -404,6 +405,33 @@ jobs:
             --partition-id ${{ matrix.part }} \
             --total-partitions 2
 
+  quantization-test:
+      needs: [check-changes, stage-a-test-1]
+      if: always() && !failure() && !cancelled() &&
+        ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
+      runs-on: 1-gpu-runner
+      steps:
+        - name: Checkout code
+          uses: actions/checkout@v4
+
+        - name: Download artifacts
+          if: needs.check-changes.outputs.sgl_kernel == 'true'
+          uses: actions/download-artifact@v4
+          with:
+            path: sgl-kernel/dist/
+            merge-multiple: true
+            pattern: wheel-python3.10-cuda12.9
+
+        - name: Install dependencies
+          run: |
+            CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} bash scripts/ci/ci_install_dependency.sh
+            pip install "bitsandbytes>=0.44.0"
+        - name: Run test
+          timeout-minutes: 30
+          run: |
+            cd test/srt
+            python3 run_suite.py --suite quantization_test
+
   unit-test-backend-1-gpu:
     needs: [check-changes, stage-a-test-1]
     if: always() && !failure() && !cancelled() &&
@@ -988,12 +1016,12 @@ jobs:
         sgl-kernel-unit-test,
         sgl-kernel-mla-test,
         sgl-kernel-benchmark-test,
-        sgl-kernel-b200-test,
 
         multimodal-gen-test-1-gpu,
         multimodal-gen-test-2-gpu,
 
         stage-a-test-1,
+        quantization-test,
         unit-test-backend-1-gpu,
         unit-test-backend-2-gpu,
         unit-test-backend-4-gpu,

.github/workflows/quantization-test.yml

@@ -1,43 +0,0 @@
-name: Quantization Test
-
-on:
-  push:
-    branches: [ main ]
-    paths:
-      - "python/**"
-      - "!python/sglang/multimodal_gen/**"
-      - "scripts/ci/**"
-      - "test/**"
-      - ".github/workflows/quantization-test.yml"
-  pull_request:
-    branches: [ main ]
-    paths:
-      - "python/**"
-      - "!python/sglang/multimodal_gen/**"
-      - "scripts/ci/**"
-      - "test/**"
-      - ".github/workflows/quantization-test.yml"
-  workflow_dispatch:
-
-concurrency:
-  group: quantization-test-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  quantization-test:
-    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
-    runs-on: 1-gpu-runner
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Install dependencies
-        run: |
-          bash scripts/ci/ci_install_dependency.sh
-          pip install "bitsandbytes>=0.44.0"
-
-      - name: Run Quantization tests
-        timeout-minutes: 30
-        run: |
-          cd test/srt
-          python3 run_suite.py --suite quantization_test