New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

v100 cannot calculate bf16 #91

Open

ganganngannn opened this issue Feb 22, 2024 · 2 comments

ganganngannn commented Feb 22, 2024

Hello, how do I modify the configuration if I want to use it on 32G v100?

divergentti commented Mar 1, 2024 •

edited

Loading

Do you mean run.py line 39 error? I checked how automatic1111 .devices.py is structured and I tried:

device = "cuda"
dtype = torch.float16
.
.
.
with torch.cuda.amp.autocast(dtype=torch.float16):

and with 32, but results are bad.

FurkanGozukara commented Mar 22, 2024

we added fp16 support fully working : #125

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment