Skip to content

Fix duplicate safetensors.load_file call in _onload_from_disk #3

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

Fix duplicate safetensors.load_file call in _onload_from_disk #3

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
7 changes: 3 additions & 4 deletions diffusers/src/diffusers/hooks/group_offloading.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -259,17 +259,16 @@ def _onload_from_disk(self):
current_stream = self._torch_accelerator_module.current_stream() if self.record_stream else None

with context:
# Load to CPU (if using streams) or directly to target device, pin, and async copy to device
device = str(self.onload_device) if self.stream is None else "cpu"
loaded_tensors = safetensors.torch.load_file(self.safetensors_file_path, device=device)

if self.stream is not None:
# Load to CPU, pin memory, then async transfer to device
loaded_tensors = safetensors.torch.load_file(self.safetensors_file_path, device="cpu")
for key, tensor_obj in self.key_to_tensor.items():
pinned_tensor = loaded_tensors[key].pin_memory()
tensor_obj.data = pinned_tensor.to(self.onload_device, non_blocking=self.non_blocking)
if self.record_stream:
tensor_obj.data.record_stream(current_stream)
else:
# Load directly to target device
onload_device = (
self.onload_device.type if isinstance(self.onload_device, torch.device) else self.onload_device
)
Expand Down