Skip to content
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

More accurate check for enabling cuDNN benchmark on 16XX cards #12924

Merged
merged 1 commit into from
Sep 9, 2023
Merged

More accurate check for enabling cuDNN benchmark on 16XX cards #12924

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion modules/devices.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,8 @@ def enable_tf32():

# enabling benchmark option seems to enable a range of cards to do fp16 when they otherwise can't
# see https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/4407
if any(torch.cuda.get_device_capability(devid) == (7, 5) for devid in range(0, torch.cuda.device_count())):
device_id = (int(shared.cmd_opts.device_id) if shared.cmd_opts.device_id.isdigit() else 0) or torch.cuda.current_device()
if torch.cuda.get_device_capability(device_id) == (7, 5) and torch.cuda.get_device_name(device_id).startswith("NVIDIA GeForce GTX 16"):
torch.backends.cudnn.benchmark = True

torch.backends.cuda.matmul.allow_tf32 = True
Expand Down