Skip to content
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

[BUG] MTP inference confuse #712

Open
niyunsheng opened this issue Feb 24, 2025 · 0 comments
Open

[BUG] MTP inference confuse #712

niyunsheng opened this issue Feb 24, 2025 · 0 comments

Comments

@niyunsheng
Copy link

Describe the bug
A clear and concise description of what the bug is.

In the paper, hnrom is before enorm, but in the open source code of sglang, enorm is before hnorm.

I do think the code in SGLang is Right, torch.cat((enorm_hidden, hnorm_hidden),dim=-1).

Image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant