MCPcopy Create free account
hub / github.com/NVIDIA/TensorRT-LLM / abort_request

Method abort_request

tensorrt_llm/executor/ray_executor.py:284–288  ·  view source on GitHub ↗
(self, request_id: int)

Source from the content-addressed store, hash-verified

282 return sorted(gpu_ids)
283
284 def abort_request(self, request_id: int) -> None:
285 self.call_all_ray_workers("abort_request",
286 leader_only=True,
287 async_call=False,
288 request_id=request_id)
289
290 def shutdown(self):
291 if hasattr(self, '_shutdown_event') and self._shutdown_event.is_set():

Callers

nothing calls this directly

Calls 1

call_all_ray_workersMethod · 0.95

Tested by

no test coverage detected