[diffusion] CI: enable UT (#20690)

.github/workflows/pr-test.yml

@@ -1245,6 +1245,45 @@ jobs:
         with:
           artifact-suffix: ${{ matrix.part }}
 
+  multimodal-gen-unit-test:
+    needs: [check-changes, call-gate, sgl-kernel-build-wheels]
+    if: |
+      always() &&
+      (
+        (inputs.target_stage == 'multimodal-gen-unit-test') ||
+        (
+          !inputs.target_stage &&
+          ((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
+          needs.check-changes.outputs.multimodal_gen == 'true'
+        )
+      )
+    runs-on: 1-gpu-runner
+    timeout-minutes: 120
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
+
+      - name: Download artifacts
+        if: needs.check-changes.outputs.sgl_kernel == 'true'
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-python3.10-cuda12.9
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+
+      - name: Run diffusion unit tests
+        timeout-minutes: 60
+        run: |
+          cd python
+          python3 sglang/multimodal_gen/test/run_suite.py --suite unit
+
   stage-c-test-4-gpu-h100:
     needs: [check-changes, call-gate, wait-for-stage-b]
     if: |
@@ -1669,6 +1708,7 @@ jobs:
         jit-kernel-unit-test-nightly,
         jit-kernel-benchmark-test,
 
+        multimodal-gen-unit-test,
         multimodal-gen-test-1-gpu,
         multimodal-gen-test-2-gpu,