[Refactor][CI] Reorganize test tree, and move slow e2e to weekly (#4951)

Signed-off-by: wangyu <410167048@qq.com>

tests/diffusion/offloader/test_diffusion_layerwise_offload.py

@@ -3,11 +3,8 @@ import pytest
 import torch
 from vllm.distributed.parallel_state import cleanup_dist_env_and_memory
 
-from tests.diffusion.offloader.test_diffusion_cpu_offload import (
-    _GATED_MODELS,
-    _skip_if_gated_repo_inaccessible,
-)
 from tests.helpers.env import DeviceMemoryMonitor
+from tests.helpers.mark import hardware_test
 from tests.helpers.runtime import OmniRunner
 from vllm_omni.inputs.data import OmniDiffusionSamplingParams
 from vllm_omni.platforms import current_omni_platform
@@ -23,6 +20,19 @@ IMAGE_VIDEO_MODELS = {
 
 MODELS = {**AUDIO_MODEL, **IMAGE_VIDEO_MODELS}
 
+LAYERWISE_MODEL_CASES = [
+    pytest.param(
+        "stabilityai/stable-audio-open-1.0",
+        marks=[pytest.mark.full_model, pytest.mark.diffusion],
+        id="stable_audio",
+    ),
+    pytest.param(
+        "riverclouds/qwen_image_random",
+        marks=[pytest.mark.core_model, pytest.mark.diffusion],
+        id="qwen_image_random",
+    ),
+]
+
 AUDIO_MODEL_PARAMS = {
     "runner_params": {},
     "sampler_params": {},
@@ -91,7 +101,8 @@ def run_inference(
     return peak, output
 
 
-@pytest.mark.parametrize("model_name", list(MODELS.keys()))
+@hardware_test(res={"cuda": "L4", "rocm": "MI325"})
+@pytest.mark.parametrize("model_name", LAYERWISE_MODEL_CASES)
 def test_layerwise_offload_diffusion_model(model_name: str):
     """Test that layerwise offloading reduces GPU memory usage.
 
@@ -100,8 +111,6 @@ def test_layerwise_offload_diffusion_model(model_name: str):
     offloader keeps only a single transformer block on GPU at a time, with
     prefetching for compute-memory overlap.
     """
-    if model_name in _GATED_MODELS:
-        _skip_if_gated_repo_inaccessible(model_name)
     try:
         # Run without layerwise offloading (baseline)
         no_offload_peak_memory, output_no_offload = run_inference(model_name, layerwise_offload=False)
@@ -111,10 +120,7 @@ def test_layerwise_offload_diffusion_model(model_name: str):
         layerwise_offload_peak_memory, output_offload = run_inference(model_name, layerwise_offload=True)
         cleanup_dist_env_and_memory()
     except ValueError as exc:
-        # omni_snapshot_download wraps GatedRepoError in a ValueError.
-        # If the pre-flight guard above did not catch it (e.g. partial
-        # HF_TOKEN where config.json is accessible but weight shards are
-        # blocked), skip instead of failing.
+        # omni_snapshot_download wraps GatedRepoError in a ValueError; skip instead of failing.
         if "Access to model" in str(exc) and "is restricted" in str(exc):
             pytest.skip(
                 f"Skipping: gated HF repo {model_name!r} inaccessible "