[diffusion] CI: add run_suite to multimodal_gen CI (#13791)

.github/workflows/pr-test.yml

@@ -359,19 +359,11 @@ jobs:
       fail-fast: false
       max-parallel: 5
       matrix:
-        test_file: ["test_server_perf_a.py", "test_server_perf_b.py"]
+        part: [0, 1]
     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=${{needs.check-changes.outputs.sgl_kernel}} bash scripts/ci/ci_install_dependency.sh diffusion
@@ -380,25 +372,25 @@ jobs:
         timeout-minutes: 60
         run: |
           cd python
-          pytest -s -v --log-cli-level=INFO sglang/multimodal_gen/test/server/${{ matrix.test_file }}
+          python3 sglang/multimodal_gen/test/run_suite.py \
+            --suite 1-gpu \
+            --partition-id ${{ matrix.part }} \
+            --total-partitions 2 \
 
 
   multimodal-gen-test-2-gpu:
     needs: [check-changes, sgl-kernel-build-wheels]
     if: (always() && !failure() && !cancelled()) && needs.check-changes.outputs.multimodal_gen == 'true'
     runs-on: 2-gpu-runner
+    strategy:
+      fail-fast: false
+      max-parallel: 5
+      matrix:
+        part: [0, 1]
     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 diffusion
@@ -407,7 +399,10 @@ jobs:
         timeout-minutes: 60
         run: |
           cd python
-          pytest -s -v --log-cli-level=INFO sglang/multimodal_gen/test/server/test_server_perf_2_gpu.py
+          python3 sglang/multimodal_gen/test/run_suite.py \
+            --suite 2-gpu \
+            --partition-id ${{ matrix.part }} \
+            --total-partitions 2
 
   unit-test-backend-1-gpu:
     needs: [check-changes, stage-a-test-1]