Skip to content

[lora] only remove hooks that we add back #11768

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 2 commits into from
Jun 24, 2025
Merged

[lora] only remove hooks that we add back #11768

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e452ff1
up
yiyixuxu Jun 22, 2025
652dca9
Merge branch 'main' into update-remove-hooks
yiyixuxu Jun 23, 2025
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
3 changes: 2 additions & 1 deletion src/diffusers/loaders/lora_base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -442,7 +442,8 @@ def _func_optionally_disable_offloading(_pipeline):
logger.info(
"Accelerate hooks detected. Since you have called `load_lora_weights()`, the previous hooks will be first removed. Then the LoRA parameters will be loaded and the hooks will be applied again."
)
remove_hook_from_module(component, recurse=is_sequential_cpu_offload)
if is_sequential_cpu_offload or is_model_cpu_offload:
Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

cc @sayakpaul
can you double check here? I'm not sure why we need to remove the hooks, but since we only add back sequential_cpu and model_cpu hooks (

diffusers/src/diffusers/loaders/lora_base.py

Line 409 in 7fc53b5

if is_model_cpu_offload:
), we should only remove these 2 types

remove_hook_from_module(component, recurse=is_sequential_cpu_offload)

return (is_model_cpu_offload, is_sequential_cpu_offload)

Expand Down
3 changes: 2 additions & 1 deletion src/diffusers/loaders/textual_inversion.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -427,7 +427,8 @@ def load_textual_inversion(
logger.info(
"Accelerate hooks detected. Since you have called `load_textual_inversion()`, the previous hooks will be first removed. Then the textual inversion parameters will be loaded and the hooks will be applied again."
)
remove_hook_from_module(component, recurse=is_sequential_cpu_offload)
if is_sequential_cpu_offload or is_model_cpu_offload:
remove_hook_from_module(component, recurse=is_sequential_cpu_offload)

# 7.2 save expected device and dtype
device = text_encoder.device
Expand Down
Loading