Skip to content

support skip atten in export #16104

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
meta-codesync merged 1 commit into from
Dec 8, 2025
Merged

support skip atten in export #16104

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: 7 additions & 0 deletions examples/models/llama/llama_transformer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -272,6 +272,13 @@ def construct_transformer(model_args: ModelArgs) -> Transformer:
norm_eps=model_args.norm_eps,
)
)
elif (
model_args.layer_types
and model_args.layer_types[layer_id] == "skip_attention"
Copy link
Contributor

@lucylq lucylq Dec 8, 2025

Choose a reason for hiding this comment

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

Is 'skip_attention' standard?

Copy link

@Hanxian97 Hanxian97 Dec 8, 2025

Choose a reason for hiding this comment

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

yes it is a standard name if we want to call https://github.com/pytorch/executorch/blob/main/examples/models/llama/attention.py#L525

):
attention = AttentionSkip()
transformer_block = TransformerBlock(model_args, attention)
layers.append(transformer_block)
else:
attention = cls(
model_args, layer_id, rope, **model_args.attention_kwargs
Expand Down
Loading