Skip to content

[Model] Add support for nvidia/Llama-3_3-Nemotron-Super-49B-v1 #5073

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.

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
wants to merge 13 commits into
base: main
Choose a base branch
from

Conversation

kylehh
Copy link

@kylehh kylehh commented Apr 4, 2025

Motivation

Add support for nvidia/Llama-3_3-Nemotron-Super-49B-v1

Modifications

Migration nemotron_nas from vllm

Checklist

@merrymercy merrymercy added the ready-to-merge The PR is ready to merge after the CI is green. label Apr 21, 2025
@@ -411,6 +425,375 @@ class LayerFn(Protocol):
def __call__(self, layer_id: int, prefix: str) -> torch.nn.Module: ...


class PPMissingLayer(torch.nn.Identity):
Copy link
Contributor

Choose a reason for hiding this comment

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

Do not add these first. Can you drop all of them?

Copy link
Author

Choose a reason for hiding this comment

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

Missinglayer class was migrated from vllm implementation, which was created by Nemotron team. Keep it for code consistent and future proof. Do these cause the failure of CI pipeline?

@zhyncs
Copy link
Member

zhyncs commented Jul 5, 2025

@kylehh please rebase. thanks.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ready-to-merge The PR is ready to merge after the CI is green.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants