[CI] Restructure vLLM-Omni Test Layout, Fixture Scope, and Support Modules (#2620)

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

tests/e2e/offline_inference/test_diffusion_layerwise_offload.py

@@ -2,8 +2,8 @@ import pytest
 import torch
 from vllm.distributed.parallel_state import cleanup_dist_env_and_memory
 
-from tests.conftest import OmniRunner
-from tests.utils import DeviceMemoryMonitor
+from tests.helpers.env import DeviceMemoryMonitor
+from tests.helpers.runtime import OmniRunner
 from vllm_omni.inputs.data import OmniDiffusionSamplingParams
 from vllm_omni.platforms import current_omni_platform