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

The setting of experiments #31

Open
YingYellow opened this issue May 22, 2024 · 0 comments
Open

The setting of experiments #31

YingYellow opened this issue May 22, 2024 · 0 comments

Comments

@YingYellow
Copy link

Hi, I have a question about the setting of KV Cache Budget. In the code, it sets a fixed HH_SIZE and RECENT_SIZE, but in the paper, the experiments are performed under various total KV Cache Budgets (%). So given a KV cache budget, like 20%, how does the KV cache split between the heavy hitter tokens and the recent tokens?

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