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
When i use Diffusors without tomesd the total memory usage in nvidia-smi is 3966MiB.
But when i use it with tomesd ( using the example in the readme ) , the usage on nvidia-smi is still the same.
Any idea whats happening?
The text was updated successfully, but these errors were encountered:
I believe someone looked into this before and found that diffusers was already using memory efficient attention, which saves most of the memory that ToMe would have saved anyway. The numbers in the paper are for the original implementation of stable diffusion.
When i use Diffusors without tomesd the total memory usage in nvidia-smi is 3966MiB.
But when i use it with tomesd ( using the example in the readme ) , the usage on nvidia-smi is still the same.
Any idea whats happening?
The text was updated successfully, but these errors were encountered: