Skip to content

[pull] master from Comfy-Org:master #884

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鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pull merged 1 commit into from
Jun 10, 2026
Merged

[pull] master from Comfy-Org:master #884

Show file tree
Hide file tree
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
6 changes: 4 additions & 2 deletions comfy/model_management.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -534,8 +534,10 @@ def aotriton_supported(gpu_arch):
except:
pass

if torch.cuda.is_available() and torch.backends.cudnn.is_available() and PerformanceFeature.AutoTune in args.fast:
torch.backends.cudnn.benchmark = True

def set_cudnn_benchmark():
if torch.cuda.is_available() and torch.backends.cudnn.is_available():
torch.backends.cudnn.benchmark = PerformanceFeature.AutoTune in args.fast

try:
if torch_version_numeric >= (2, 5):
Expand Down
5 changes: 5 additions & 0 deletions main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -490,6 +490,11 @@ def start_comfyui(asyncio_loop=None):
init_custom_nodes=(not args.disable_all_custom_nodes) or len(args.whitelist_custom_nodes) > 0,
init_api_nodes=not args.disable_api_nodes
))

# Re-apply Comfy's cuDNN benchmark policy after custom-node imports. Benchmark
# mode can request near-card-sized autotune workspaces, and some custom nodes set it at import time.
comfy.model_management.set_cudnn_benchmark()

hook_breaker_ac10a0.restore_functions()

cuda_malloc_warning()
Expand Down
Loading