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

【Sync】Release/2.0.1 (#2745)

Browse Source 
* add rl qwen model support

* fix

* fix
This commit is contained in:
gaoziyuan
2025-07-08 14:38:18 +08:00
committed by GitHub
parent ea787d8f62
commit 6851489425
13 changed files with 438 additions and 171 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
fastdeploy/model_executor/layers/attention/flash_attn_backend.py
View File

@@ -21,7 +21,11 @@ from dataclasses import dataclass, field
from typing import List, Optional
import paddle
from paddle.nn.functional.flash_attention import flash_attention_v3_varlen
try:
from paddle.nn.functional.flash_attention import flash_attention_v3_varlen
except:
flash_attention_v3_varlen = None
from fastdeploy.config import FDConfig
from fastdeploy.model_executor.layers.attention.attention import Attention