apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

【FIX】Change the name of sparse attn from moba to plas (#3845)

Browse Source 
* 更新文档

* 更新文档

* 更新文档

* 更新文档

* 修改moba为plas

* code style

* update ci

* code style

* update ci
This commit is contained in:
yangjianfengo1
2025-09-09 10:56:50 +08:00
committed by GitHub
parent de34222842
commit e31c8f7336
13 changed files with 150 additions and 150 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/engine/engine.py
View File

@@ -493,7 +493,7 @@ class LLMEngine:
f" --early_stop_config '{self.cfg.early_stop_config.to_json_string()}'"
f" --reasoning_parser {self.cfg.reasoning_parser}"
f" --load_choices {self.cfg.load_config.load_choices}"
f" --moba_attention_config '{self.cfg.moba_attention_config.to_json_string()}'"
f" --plas_attention_config '{self.cfg.plas_attention_config.to_json_string()}'"
f" --ips {ips}"
)