Skip to content

Fix Python 3.12 VRAM spikes with CUDNN benchmark #10026

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

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix Python 3.12 VRAM spikes with CUDNN benchmark #10026

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
5 changes: 4 additions & 1 deletion comfy/ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,10 @@ def scaled_dot_product_attention(q, k, v, *args, **kwargs):
cast_to = comfy.model_management.cast_to #TODO: remove once no more references

if torch.cuda.is_available() and torch.backends.cudnn.is_available() and PerformanceFeature.AutoTune in args.fast:
torch.backends.cudnn.benchmark = True
import sys
# Skip CUDNN benchmark on Python 3.12 due to VRAM allocation issues with model wrappers
if sys.version_info[:2] != (3, 12):
torch.backends.cudnn.benchmark = True

def cast_to_input(weight, input, non_blocking=False, copy=True):
return comfy.model_management.cast_to(weight, input.dtype, input.device, non_blocking=non_blocking, copy=copy)
Expand Down