298977887/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-03-15 05:57:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix typo.

Browse Source 
Let me know if this slows things down on 2000 series and below.
This commit is contained in:
comfyanonymous 2025-02-18 07:28:33 -05:00
parent 31e54b7052
commit b07258cef2
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
comfy/model_management.py
View File

@ -1121,7 +1121,7 @@ def should_use_bf16(device=None, model_params=0, prioritize_performance=True, ma
bf16_works = torch.cuda.is_bf16_supported()
if bf16_works or manual_cast:
if bf16_works and manual_cast:
free_model_memory = maximum_vram_for_weights(device)
if (not prioritize_performance) or model_params * 4 > free_model_memory:
return True