mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-05 08:37:06 +08:00
@@ -148,9 +148,9 @@ class GPUModelRunner(ModelRunnerBase):
|
||||
self.local_rank + int(self.parallel_config.engine_worker_queue_port)
|
||||
)
|
||||
|
||||
def prefill_finished(self):
|
||||
def exist_prefill(self):
|
||||
"""
|
||||
Check whether prefill stage finished
|
||||
check whether prefill stage exist
|
||||
"""
|
||||
if int(paddle.max(self.share_inputs["seq_lens_encoder"])) != 0:
|
||||
return 1
|
||||
|
Reference in New Issue
Block a user