Skip to content

Optimize Linear Layer Operations in LoRALinear Class #12

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

Optimize Linear Layer Operations in LoRALinear Class #12

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
5 changes: 3 additions & 2 deletions src/mistral_inference/lora.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,8 +69,9 @@ def ignore_missing_keys(m: nn.Module, incompatible_keys: NamedTuple) -> None:
self.register_load_state_dict_post_hook(ignore_missing_keys)

def forward(self, x: torch.Tensor) -> torch.Tensor:
lora = self.lora_B(self.lora_A(x))
result: torch.Tensor = self.linear(x) + lora * self.scaling
lora_A_result = self.lora_A(x)
Copy link
Owner Author

@mandlinsarah mandlinsarah Aug 9, 2024

Choose a reason for hiding this comment

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

did you check if its working ?

Copy link
Owner Author

@mandlinsarah mandlinsarah Aug 10, 2024

Choose a reason for hiding this comment

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

Yes, I verified the changes and confirmed that the functionality is working as expected.

lora = self.lora_B(lora_A_result)
result = self.linear(x) + lora * self.scaling
Copy link
Owner Author

@mandlinsarah mandlinsarah Aug 10, 2024

Choose a reason for hiding this comment

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

can you explain this line

return result

def _load_from_state_dict(self, state_dict: Dict[str, Any], prefix: str, *args, **kwargs) -> None: # type: ignore[no-untyped-def]
Expand Down