vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-13 00:29:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

fix flashinfer precision

Browse source
This commit is contained in:
Atream 2025-03-07 14:07:00 +00:00
parent 96d75d53df
commit d453c320f1
5 changed files with 151 additions and 61 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ktransformers/operators/attention.py
View file

@ -25,7 +25,7 @@ from ktransformers.operators.triton_attention import decode_attention_fwd_groupe
import os
from ktransformers.operators.flashinfer_wrapper import flashinfer_enabled
if flashinfer_enabled:
from ktransformers.operators.flashinfer_wrapper import MLAWrapperSingleton, attention_ref
from ktransformers.operators.flashinfer_wrapper import MLAWrapperSingleton
logger = logging.getLogger("attention")