Skip to content

torch.load always to cpu first #308

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
johannaSommer merged 1 commit into from
Aug 20, 2025
Merged

torch.load always to cpu first #308

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
4 changes: 2 additions & 2 deletions src/pruna/engine/load.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -329,10 +329,10 @@ def load_pickled(path: str | Path, smash_config: SmashConfig, **kwargs) -> Any:
model = torch.load(
Path(path) / PICKLED_FILE_NAME,
weights_only=False,
map_location=target_device,
map_location="cpu",
**filter_load_kwargs(torch.load, kwargs),
)
# for cpu/cuda this will just continue as its on the correct device, for accelerate it will now distribute / cast
# move to target device, for accelerate it will now distribute / cast
move_to_device(model, target_device, device_map=smash_config.device_map)
return model

Expand Down