[Test] Unify L2/L3 test layout, Buildkite steps, and test helpers (#2556)

Signed-off-by: wangyu <410167048@qq.com>
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com>
Co-authored-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>

tests/diffusion/cache/test_teacache.py

@@ -0,0 +1,73 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+"""
+System test for TeaCache backend.
+
+This test verifies that TeaCache acceleration works correctly with diffusion models.
+It uses minimal settings to keep test time short for CI.
+"""
+
+import pytest
+import torch
+
+from tests.helpers.mark import hardware_test
+from tests.helpers.runtime import OmniRunner
+from vllm_omni.inputs.data import OmniDiffusionSamplingParams
+from vllm_omni.outputs import OmniRequestOutput
+from vllm_omni.platforms import current_omni_platform
+
+# Use random weights model for testing
+models = ["riverclouds/qwen_image_random"]
+
+
+@pytest.mark.core_model
+@pytest.mark.diffusion
+@pytest.mark.cache
+@hardware_test(res={"cuda": "L4", "rocm": "MI325", "xpu": "B60"})
+@pytest.mark.parametrize("model_name", models)
+def test_teacache(model_name: str):
+    """Test TeaCache backend with diffusion model."""
+    # Configure TeaCache with default settings for fast testing
+    cache_config = {
+        "rel_l1_thresh": 0.2,  # Default threshold
+    }
+    with OmniRunner(
+        model_name,
+        cache_backend="tea_cache",
+        cache_config=cache_config,
+    ) as runner:
+        # Use minimal settings for fast testing
+        height = 256
+        width = 256
+        num_inference_steps = 4  # Minimal steps for fast test
+
+        outputs = runner.omni.generate(
+            "a photo of a cat sitting on a laptop keyboard",
+            OmniDiffusionSamplingParams(
+                height=height,
+                width=width,
+                num_inference_steps=num_inference_steps,
+                guidance_scale=0.0,
+                generator=torch.Generator(current_omni_platform.device_type).manual_seed(42),
+                num_outputs_per_prompt=1,  # Single output for speed
+            ),
+        )
+        # Extract images from request_output['images']
+        first_output = outputs[0]
+        assert first_output.final_output_type == "image"
+        if not hasattr(first_output, "request_output") or not first_output.request_output:
+            raise ValueError("No request_output found in OmniRequestOutput")
+
+        req_out = first_output.request_output
+        if not isinstance(req_out, OmniRequestOutput) or not hasattr(req_out, "images"):
+            raise ValueError("Invalid request_output structure or missing 'images' key")
+
+        images = req_out.images
+
+        # Verify generation succeeded
+        assert images is not None
+        assert len(images) == 1
+        # Check image size
+        assert images[0].width == width
+        assert images[0].height == height