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

Method report_device_ids

tensorrt_llm/executor/ray_executor.py:278–282  ·  view source on GitHub ↗
(self)

Source from the content-addressed store, hash-verified

276 return result
277
278 def report_device_ids(self) -> list[str]:
279 gpu_ids = self.call_all_ray_workers("report_device_id",
280 leader_only=False,
281 async_call=False)
282 return sorted(gpu_ids)
283
284 def abort_request(self, request_id: int) -> None:
285 self.call_all_ray_workers("abort_request",

Callers

nothing calls this directly

Calls 1

call_all_ray_workersMethod · 0.95

Tested by

no test coverage detected