v100 cannot calculate bf16

[ganganngannn]

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

[Jari Hiltunen]

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.

[Furkan Gözükara]

we added fp16 support fully working : #125