MCPcopy Create free account
hub / github.com/PaddlePaddle/FastDeploy / sot_warmup

Method sot_warmup

fastdeploy/worker/xpu_model_runner.py:1515–1523  ·  view source on GitHub ↗
(self)

Source from the content-addressed store, hash-verified

1513
1514 @sot_warmup_guard(True)
1515 def sot_warmup(self) -> None:
1516 start_time = time.perf_counter()
1517 for batch_size in self.sot_warmup_sizes:
1518 self._dummy_run(
1519 num_tokens=self.parallel_config.max_num_batched_tokens,
1520 batch_size=batch_size,
1521 )
1522 logger.info(f"SOT warmup the model with the batch size:{batch_size}")
1523 logger.info(f"SOT warmup took {time.perf_counter() - start_time} seconds")
1524
1525 def execute_model(
1526 self,

Callers

nothing calls this directly

Calls 2

_dummy_runMethod · 0.95
infoMethod · 0.45

Tested by

no test coverage detected