298977887/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-04-20 11:23:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

pytorch xpu should be flash or mem efficient attention?

Browse Source
This commit is contained in:
comfyanonymous 2024-06-04 17:44:14 -04:00
parent 20447e9ec9
commit b1fd26fe9e
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
comfy/model_management.py
View File

@ -693,6 +693,8 @@ def pytorch_attention_flash_attention():
#TODO: more reliable way of checking for flash attention? #TODO: more reliable way of checking for flash attention?
if is_nvidia(): #pytorch flash attention only works on Nvidia if is_nvidia(): #pytorch flash attention only works on Nvidia
return True return True
if is_intel_xpu():
return True
return False return False
def force_upcast_attention_dtype(): def force_upcast_attention_dtype():