apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-21 07:40:37 +08:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
Wanglongzhi2001
2025-01-09 07:16:13 +00:00
parent ed5f65a694
commit 99d0921049
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
llm/server/server/engine/infer.py
View File

@@ -500,8 +500,8 @@ class ModelRunner:
if self.proposer is not None: if self.proposer is not None:
self.proposer.run( self.proposer.run(
self.share_inputs, self.share_inputs,
real_batch_size=self.args.max_batch_size, real_batch_size=seq_lens_this_time.shape[0],
seq_lens_this_time=self.share_inputs["seq_lens_this_time"], seq_lens_this_time=seq_lens_this_time,
) )
self.infer_engine.predictor.run() self.infer_engine.predictor.run()