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

6
fastdeploy/platforms/cuda.py
View File

@@ -64,9 +64,9 @@ class CUDAPlatform(Platform):
elif selected_backend == _Backend.FLASH_ATTN:
logger.info("Using FLASH ATTN backend.")
return "fastdeploy.model_executor.layers.attention.FlashAttentionBackend"
elif selected_backend == _Backend.MOBA_ATTN:
logger.info("Using MOBA ATTN backend.")
return "fastdeploy.model_executor.layers.attention.MobaAttentionBackend"
elif selected_backend == _Backend.PLAS_ATTN:
logger.info("Using PLAS ATTN backend.")
return "fastdeploy.model_executor.layers.attention.PlasAttentionBackend"
else:
raise ValueError(
"Invalid attention backend you specified.\n"