Skip to content

mm: discard async errors from pinning failures #10738

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
comfyanonymous merged 1 commit into from
Dec 29, 2025
Merged

mm: discard async errors from pinning failures #10738

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
14 changes: 14 additions & 0 deletions comfy/model_management.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1126,6 +1126,16 @@ def cast_to_device(tensor, device, dtype, copy=False):

PINNING_ALLOWED_TYPES = set(["Parameter", "QuantizedTensor"])

def discard_cuda_async_error():
try:
a = torch.tensor([1], dtype=torch.uint8, device=get_torch_device())
b = torch.tensor([1], dtype=torch.uint8, device=get_torch_device())
_ = a + b
torch.cuda.synchronize()
except torch.AcceleratorError:
#Dump it! We already know about it from the synchronous return
pass

def pin_memory(tensor):
global TOTAL_PINNED_MEMORY
if MAX_PINNED_MEMORY <= 0:
Expand Down Expand Up @@ -1158,6 +1168,8 @@ def pin_memory(tensor):
PINNED_MEMORY[ptr] = size
TOTAL_PINNED_MEMORY += size
return True
else:
discard_cuda_async_error()

return False

Expand Down Expand Up @@ -1186,6 +1198,8 @@ def unpin_memory(tensor):
if len(PINNED_MEMORY) == 0:
TOTAL_PINNED_MEMORY = 0
return True
else:
discard_cuda_async_error()

return False

Expand Down