apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-08 10:00:29 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Revert "[Feature] block sparse attention (#3209)" (#3647)

Browse Source 
This reverts commit 646a0c2fd8.
This commit is contained in:
Jiang-Jia-Jun
2025-08-27 17:35:04 +08:00
committed by GitHub
parent b2afdf4fc6
commit c694fa2879
31 changed files with 10 additions and 6507 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/model_executor/layers/attention/__init__.py
View File

@@ -20,7 +20,6 @@ from .block_multihead_attn_backend import BlockAttentionBackend
from .flash_attn_backend import FlashAttentionBackend
from .iluvatar_attn_backend import IluvatarAttnBackend
from .mla_attention_backend import MLAAttentionBackend
from .moba_attention_backend import MobaAttentionBackend
from .native_paddle_backend import PaddleNativeAttnBackend
from .xpu_attn_backend import XPUAttentionBackend
@@ -35,5 +34,4 @@ __all__ = [
"IluvatarAttnBackend",
"BlockAttentionBackend",
"Attention",
"MobaAttentionBackend",
]