Method enqueue_request

tensorrt_llm/executor/ray_gpu_worker.py:253–256 · view source on GitHub ↗

(self,
                        request: GenerationRequest,
                        result_wait_queue: Queue | None = None)

Source from the content-addressed store, hash-verified

251	super().setup_engine()
252
253	def enqueue_request(self,
254	request: GenerationRequest,
255	result_wait_queue: Queue \| None = None) -> int:
256	return self._enqueue_request(request, result_wait_queue)
257
258	@control_action_decorator
259	def sleep(self, sleep_tags: List[str]):

test_enqueue_request_singleFunction · 0.45

test_enqueue_request_with_queryFunction · 0.45

test_enqueue_request_with_child_idsFunction · 0.45

test_enqueue_request_after_shutdownFunction · 0.45

test_shutdownFunction · 0.45

test_embedding_biasFunction · 0.45

test_single_requestFunction · 0.45

test_single_request_loraFunction · 0.45

test_multi_requestFunction · 0.45

test_multi_request_with_idsFunction · 0.45

test_get_num_responses_readyFunction · 0.45

test_single_request_invalid_inputsFunction · 0.45

_enqueue_requestMethod · 0.80

test_enqueue_request_singleFunction · 0.36

test_enqueue_request_with_queryFunction · 0.36

test_enqueue_request_with_child_idsFunction · 0.36

test_enqueue_request_after_shutdownFunction · 0.36

test_shutdownFunction · 0.36

test_embedding_biasFunction · 0.36

test_single_requestFunction · 0.36

test_single_request_loraFunction · 0.36

test_multi_requestFunction · 0.36

test_multi_request_with_idsFunction · 0.36

test_get_num_responses_readyFunction · 0.36

test_single_request_invalid_inputsFunction · 0.36