apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-31 03:46:40 +08:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

Adapt for iluvatar gpu (#2684)

Browse Source
This commit is contained in:
liddk1121
2025-07-07 16:53:14 +08:00
committed by GitHub
parent 2579e8fea8
commit 1b54a2831e
50 changed files with 4485 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
fastdeploy/model_executor/layers/attention/__init__.py
View File

@@ -19,9 +19,10 @@ from .flash_attn_backend import FlashAttentionBackend
from .mla_attention_backend import MLAAttentionBackend
from .native_paddle_backend import PaddleNativeAttnBackend
from .xpu_attn_backend import XPUAttentionBackend
from .iluvatar_attn_backend import IluvatarAttnBackend
__all__ = [
"AttentionBackend", "PaddleNativeAttnBackend",
"get_attention_backend", "AppendAttentionBackend", "XPUAttentionBackend",
"MLAAttentionBackend", "FlashAttentionBackend"
"MLAAttentionBackend", "FlashAttentionBackend", "IluvatarAttnBackend"
]