-
Notifications
You must be signed in to change notification settings - Fork 2.3k
[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
base: main
Are you sure you want to change the base?
Conversation
@@ -411,6 +425,375 @@ class LayerFn(Protocol): | |||
def __call__(self, layer_id: int, prefix: str) -> torch.nn.Module: ... | |||
|
|||
|
|||
class PPMissingLayer(torch.nn.Identity): |
There was a problem hiding this comment.
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?
There was a problem hiding this comment.
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?
@kylehh please rebase. thanks. |
Motivation
Add support for nvidia/Llama-3_3-Nemotron-Super-49B-v1
Modifications
Migration nemotron_nas from vllm
Checklist