Skip to content

Conversation

zikun-li
Copy link
Collaborator

@zikun-li zikun-li commented Apr 3, 2025

Fuse gate and up projection

@zikun-li
Copy link
Collaborator Author

zikun-li commented Apr 3, 2025

There is currently a memory issue in this code.

@zikun-li
Copy link
Collaborator Author

zikun-li commented Apr 3, 2025

There's an issue that the output shape of the Linear operator and the input shape of the Silu operator following it don't match.

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

Successfully merging this pull request may close these issues.

2 participants