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

dcu adapter ernie45t (#2756)

Browse Source 
Co-authored-by: lifu <lifu@sugon.com>
Co-authored-by: yongqiangma <xing.wo@163.com>
This commit is contained in:
lifulll
2025-07-09 18:56:27 +08:00
committed by GitHub
parent 03a74995b8
commit 1f28bdf994
30 changed files with 1133 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
fastdeploy/model_executor/layers/attention/__init__.py
View File

@@ -20,9 +20,11 @@ from .mla_attention_backend import MLAAttentionBackend
from .native_paddle_backend import PaddleNativeAttnBackend
from .xpu_attn_backend import XPUAttentionBackend
from .iluvatar_attn_backend import IluvatarAttnBackend
from .block_multihead_attn_backend import BlockAttentionBackend
__all__ = [
"AttentionBackend", "PaddleNativeAttnBackend",
"get_attention_backend", "AppendAttentionBackend", "XPUAttentionBackend",
"MLAAttentionBackend", "FlashAttentionBackend", "IluvatarAttnBackend"
"MLAAttentionBackend", "FlashAttentionBackend", "IluvatarAttnBackend",
"BlockAttentionBackend"
]