[Test] L2 & L3 Test Case Stratification Design for Omni Model

.buildkite/pipeline.yml

@@ -17,14 +17,6 @@ steps:
     agents:
       queue: "cpu_queue_premerge"
 
-  # - label: "Test on NPU"
-  #   depends_on: ~
-  #   key: npu-test
-  #   commands:
-  #     - ".buildkite/scripts/hardware_ci/run_npu_test.sh"
-  #   agents:
-  #     queue: "ascend"
-
   - label: "Simple Unit Test"
     depends_on: image-build
     commands:
@@ -182,12 +174,13 @@ steps:
             - "/fsx/hf_cache:/fsx/hf_cache"
 
 
-  - label: "Benchmark Test"
+  - label: "Benchmark&Engine Test"
     timeout_in_minutes: 15
     depends_on: image-build
     commands:
       - export VLLM_WORKER_MULTIPROC_METHOD=spawn
       - pytest -s -v tests/benchmarks/test_serve_cli.py
+      - pytest -s -v tests/engine/test_async_omni_engine_abort.py
     agents:
       queue: "mithril-h100-pool"
     plugins:
@@ -236,6 +229,43 @@ steps:
           volumes:
             - "/fsx/hf_cache:/fsx/hf_cache"
 
+  - label: "Omni Model Test with H100"
+    timeout_in_minutes: 20
+    depends_on: image-build
+    commands:
+       - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+       - export VLLM_TEST_CLEAN_GPU_MEMORY="1"
+       - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py
+       - pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py -m "core_model" --run-level "core_model"
+    agents:
+       queue: "mithril-h100-pool"
+    plugins:
+       - kubernetes:
+           podSpec:
+             containers:
+               - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                 resources:
+                   limits:
+                     nvidia.com/gpu: 2
+                 volumeMounts:
+                   - name: devshm
+                     mountPath: /dev/shm
+                   - name: hf-cache
+                     mountPath: /root/.cache/huggingface
+                 env:
+                   - name: HF_HOME
+                     value: /root/.cache/huggingface
+             nodeSelector:
+               node.kubernetes.io/instance-type: gpu-h100-sxm
+             volumes:
+               - name: devshm
+                 emptyDir:
+                   medium: Memory
+               - name: hf-cache
+                 hostPath:
+                   path: /mnt/hf-cache
+                   type: DirectoryOrCreate
+
   - label: "Qwen3-TTS E2E Test"
     timeout_in_minutes: 10
     depends_on: image-build
@@ -256,44 +286,6 @@ steps:
           volumes:
             - "/fsx/hf_cache:/fsx/hf_cache"
 
-  # - label: "Omni Model Test with H100"
-  #   timeout_in_minutes: 30
-  #   depends_on: image-build
-  #   commands:
-  #     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  #     - export VLLM_TEST_CLEAN_GPU_MEMORY="1"
-  #     - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py
-  #     - pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py
-  #     - pytest -s -v tests/e2e/online_serving/test_async_omni.py
-  #   agents:
-  #     queue: "mithril-h100-pool"
-  #   plugins:
-  #     - kubernetes:
-  #         podSpec:
-  #           containers:
-  #             - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
-  #               resources:
-  #                 limits:
-  #                   nvidia.com/gpu: 2
-  #               volumeMounts:
-  #                 - name: devshm
-  #                   mountPath: /dev/shm
-  #                 - name: hf-cache
-  #                   mountPath: /root/.cache/huggingface
-  #               env:
-  #                 - name: HF_HOME
-  #                   value: /root/.cache/huggingface
-  #           nodeSelector:
-  #             node.kubernetes.io/instance-type: gpu-h100-sxm
-  #           volumes:
-  #             - name: devshm
-  #               emptyDir:
-  #                 medium: Memory
-  #             - name: hf-cache
-  #               hostPath:
-  #                 path: /mnt/hf-cache
-  #                 type: DirectoryOrCreate
-
   - label: "Diffusion Image Edit Test with H100 (1 GPU)"
     timeout_in_minutes: 20
     depends_on: image-build

.buildkite/test-amd.yaml

@@ -101,7 +101,7 @@ steps:
     - export VLLM_TEST_CLEAN_GPU_MEMORY="1"
     - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py
     - pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py
-    - pytest -s -v tests/e2e/online_serving/test_async_omni.py
+    - pytest -s -v tests/engine/test_async_omni_engine_abort.py
 
 - label: "Diffusion Image Edit Test"
   timeout_in_minutes: 15