[Core] Implement Diffusion Profiler Support (#709)

Signed-off-by: lishunyang <lishunyang12@163.com>
Signed-off-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>

vllm_omni/diffusion/worker/gpu_diffusion_worker.py

@@ -28,6 +28,7 @@ from vllm_omni.diffusion.distributed.parallel_state import (
     initialize_model_parallel,
 )
 from vllm_omni.diffusion.forward_context import set_forward_context
+from vllm_omni.diffusion.profiler import CurrentProfiler
 from vllm_omni.diffusion.request import OmniDiffusionRequest
 from vllm_omni.diffusion.worker.gpu_diffusion_model_runner import GPUDiffusionModelRunner
 
@@ -115,6 +116,16 @@ class GPUDiffusionWorker:
         """Generate output for the given requests."""
         return self.execute_model(requests, self.od_config)
 
+    @classmethod
+    def start_profile(cls, trace_path_template: str) -> str:
+        """Start profiling for this GPU worker."""
+        return CurrentProfiler.start(trace_path_template)
+
+    @classmethod
+    def stop_profile(cls) -> dict | None:
+        """Stop profiling and return the result dictionary."""
+        return CurrentProfiler.stop()
+
     def execute_model(self, reqs: list[OmniDiffusionRequest], od_config: OmniDiffusionConfig) -> DiffusionOutput:
         """Execute a forward pass by delegating to the model runner."""
         assert self.model_runner is not None, "Model runner not initialized"