xinyun/ComfyUI
1
0
Fork 0
mirror of https://git.datalinker.icu/comfyanonymous/ComfyUI synced 2026-08-16 03:50:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

Better memory estimation for ROCm that support mem efficient attention.

Browse Source 
There is no way to check if the card actually supports it so it assumes
that it does if you use --use-pytorch-cross-attention with yours.
This commit is contained in:
comfyanonymous 2025-02-13 08:32:36 -05:00
parent 66d579cd19
commit 1f657be9a7
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

@ -909,6 +909,8 @@ def pytorch_attention_flash_attention():
return True
if is_ascend_npu():
return True
if is_amd():
return True #if you have pytorch attention enabled on AMD it probably supports at least mem efficient attention
return False
def mac_version():