apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-26 02:14:06 +08:00
Code Issues Actions 7 Packages Projects Releases Wiki Activity

[BugFix][Optimization] Replace silent failures with catchable exceptions and informative error messages (#6533)

Browse Source 
* init

* init

* fix format

* add

* add files

* add ut

* fix some

* add ut

* add more

* add

* fix pre-commit

* fix pre-commit

* fix cover

* skip long seq

* add

* add

* fix

* remove not need

* fix set attr

* fix comments

* fix comments

* fix failed tests

---------

Co-authored-by: gongweibao <gognweibao@baidu.com>
This commit is contained in:
gongweibao
2026-03-16 21:32:43 +08:00
committed by GitHub
parent d113397b09
commit a6351dea0b
61 changed files with 1595 additions and 171 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/model_executor/layers/attention/mla_attention_backend.py
+3 -1
View File
@@ -26,10 +26,12 @@ from typing import TYPE_CHECKING, List, Optional, Tuple
import paddle
from paddle.nn.functional.flash_attention import flash_attn_unpadded
from paddleformers.utils.log import logger
try:
from paddle.nn.functional.flash_attention import flash_attention_v3_varlen
except:
except Exception as e:
logger.debug(f"flash_attention_v3_varlen not available: {e}")
flash_attention_v3_varlen = None
from fastdeploy.model_executor.layers.attention.ops import (