apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-09-30 14:22:27 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

custom all reduce support cuda graph (#2938)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* Support enabling cuda graph and custom all reduce at the same time, and fix the overwritten custom all reduce flag

* rename communication_op to communication
This commit is contained in:
zhink
2025-07-21 22:52:03 +08:00
committed by GitHub
parent ff4569f135
commit 0262ef7eb3
21 changed files with 88 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/engine/engine.py
View File

@@ -1024,7 +1024,7 @@ class LLMEngine:
"do_profile": self.do_profile,
"dynamic_load_weight": self.cfg.model_config.dynamic_load_weight,
"disable_any_whitespace": self.cfg.disable_any_whitespace,
"enable-custom-all-reduce": self.cfg.parallel_config.enable_custom_all_reduce,
"enable_custom_all_reduce": self.cfg.parallel_config.enable_custom_all_reduce,
"enable_logprob": self.cfg.enable_logprob,
"enable_mm": self.cfg.enable_mm,
}