Skip to content

Don't pin tensor if not a torch.nn.parameter.Parameter #10718

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

Merged
merged 1 commit into from
Nov 12, 2025
Merged

Don't pin tensor if not a torch.nn.parameter.Parameter #10718

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: 6 additions & 0 deletions comfy/model_management.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1107,6 +1107,9 @@ def pin_memory(tensor):
if MAX_PINNED_MEMORY <= 0:
return False

if type(tensor) is not torch.nn.parameter.Parameter:
return False

if not is_device_cpu(tensor.device):
return False

Expand All @@ -1116,6 +1119,9 @@ def pin_memory(tensor):
#on the GPU async. So dont trust the CUDA API and guard here
return False

if not tensor.is_contiguous():
return False

size = tensor.numel() * tensor.element_size()
if (TOTAL_PINNED_MEMORY + size) > MAX_PINNED_MEMORY:
return False
Expand Down