[Bugfix] remove Tongyi-MAI/Z-Image-Turbo related test from L2 ci (#1348)

Signed-off-by: dengyunyang <584797741@qq.com>

.buildkite/pipeline.yml

@@ -37,24 +37,7 @@ steps:
     timeout_in_minutes: 20
     depends_on: image-build
     commands:
-      - pytest -s -v tests/e2e/offline_inference/test_t2i_model.py
-    agents:
-      queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
-    plugins:
-      - docker#v5.2.0:
-          image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
-          always-pull: true
-          propagate-environment: true
-          environment:
-            - "HF_HOME=/fsx/hf_cache"
-          volumes:
-            - "/fsx/hf_cache:/fsx/hf_cache"
-
-  - label: "Diffusion Images API LoRA E2E"
-    timeout_in_minutes: 20
-    depends_on: image-build
-    commands:
-      - pytest -s -v tests/e2e/online_serving/test_images_generations_lora.py
+      - pytest -s -v tests/e2e/offline_inference/test_t2i_model.py -m "core_model and diffusion" --run-level "core_model"
     agents:
       queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
     plugins:
@@ -137,24 +120,6 @@ steps:
           volumes:
             - "/fsx/hf_cache:/fsx/hf_cache"
 
-  - label: "Diffusion Tensor Parallelism Test"
-    timeout_in_minutes: 20
-    depends_on: image-build
-    commands:
-      - pytest -s -v tests/e2e/offline_inference/test_zimage_parallelism.py
-    agents:
-      queue: "gpu_4_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
-    plugins:
-      - docker#v5.2.0:
-          image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
-          always-pull: true
-          propagate-environment: true
-          shm-size: "8gb"
-          environment:
-            - "HF_HOME=/fsx/hf_cache"
-          volumes:
-            - "/fsx/hf_cache:/fsx/hf_cache"
-
   - label: "Diffusion GPU Worker Test"
     timeout_in_minutes: 20
     depends_on: image-build

.buildkite/test-merge.yml

@@ -29,7 +29,7 @@ steps:
     timeout_in_minutes: 20
     depends_on: image-build
     commands:
-      - pytest -s -v tests/e2e/offline_inference/test_t2i_model.py
+      - pytest -s -v tests/e2e/offline_inference/test_t2i_model.py -m "advanced_model and diffusion" --run-level "advanced_model"
     agents:
       queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
     plugins:

tests/e2e/offline_inference/test_t2i_model.py

@@ -34,10 +34,17 @@ elif current_omni_platform.is_rocm():
 
 
 @pytest.mark.core_model
+@pytest.mark.advanced_model
 @pytest.mark.diffusion
 @hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 1, "rocm": 2})
 @pytest.mark.parametrize("model_name", models)
-def test_diffusion_model(model_name: str):
+def test_diffusion_model(model_name: str, run_level):
+    if run_level == "core_model" and model_name != "riverclouds/qwen_image_random":
+        pytest.skip()
+
+    if run_level == "advanced_model" and model_name == "riverclouds/qwen_image_random":
+        pytest.skip()
+
     m = None
     try:
         m = Omni(model=model_name)

tests/e2e/offline_inference/test_zimage_parallelism.py

@@ -154,7 +154,7 @@ def _run_zimage_generate(
         cleanup_dist_env_and_memory()
 
 
-@pytest.mark.core_model
+@pytest.mark.advanced_model
 @pytest.mark.diffusion
 @pytest.mark.parallel
 @hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})

tests/e2e/online_serving/test_images_generations_lora.py

@@ -145,7 +145,7 @@ def _basic_payload() -> dict:
     }
 
 
-@pytest.mark.core_model
+@pytest.mark.advanced_model
 @pytest.mark.diffusion
 @hardware_test(res={"cuda": "L4", "rocm": "MI325"})
 def test_images_generations_per_request_lora_switching(omni_server: OmniServer, tmp_path: Path) -> None: