apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[BugFix] fix vl performance bug (#5181)

Browse Source 
* fix vl performance bug

* update code

* update code

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
kevin
2025-11-26 21:06:52 +08:00
committed by GitHub
parent 209970836e
commit bf30f45738
2 changed files with 10 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/config.py
View File

@@ -1574,7 +1574,7 @@ class FDConfig:
self.max_prefill_batch = int(os.getenv("MAX_PREFILL_NUM", "3"))
if current_platform.is_xpu():
self.max_prefill_batch = 1
if self.model_config is not None and self.model_config.enable_mm and not envs.ENABLE_V1_KVCACHE_SCHEDULER:
if self.model_config is not None and self.model_config.enable_mm:
self.max_prefill_batch = 1 # TODO:当前多模prefill阶段只支持并行度为1,待优化
else:
self.max_prefill_batch = self.scheduler_config.max_num_seqs