-
Notifications
You must be signed in to change notification settings - Fork 23
Issues: mit-han-lab/duo-attention
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
RuntimeError: shape '[1, 3098, 6, 5, 128]' is invalid for input of size 12689408
#13
opened Dec 7, 2024 by
LuchenZhou
The issue of saving a model that has been modified with DuoAttention to local storage
#11
opened Nov 13, 2024 by
xlxcomputer
Seems like chunked pre-filling is inactive when evaluating longbench.
#9
opened Nov 8, 2024 by
BirdChristopher
ProTip!
Find all open issues with in progress development work with linked:pr.