You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Traceback (most recent call last):
File "/opt/tiger/mariana/llm-jsq/main.py", line 21, in <module>
from sageattention import sageattn
File "/opt/tiger/lab-speech/byteslim/sageattention/__init__.py", line 1, in <module>
from .core import sageattn, sageattn_varlen
File "/opt/tiger/lab-speech/byteslim/sageattention/core.py", line 47, in <module>
from .quant import per_block_int8 as per_block_int8_cuda
File "/opt/tiger/lab-speech/byteslim/sageattention/quant.py", line 20, in <module>
from . import _fused
ImportError: cannot import name '_fused' from partially initialized module 'sageattention' (most likely due to a circular import) (/opt/tiger/lab-speech/byteslim/sageattention/__init__.py)
The text was updated successfully, but these errors were encountered:
I use SageAttn like this, but got error
The text was updated successfully, but these errors were encountered: