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

How is perplexity calculated with the KV cache? #42

Open
tsengalb99 opened this issue Sep 24, 2024 · 0 comments
Open

How is perplexity calculated with the KV cache? #42

tsengalb99 opened this issue Sep 24, 2024 · 0 comments

Comments

@tsengalb99
Copy link

I've noticed QuaRot and other KV cache papers include perplexity, but it is unclear to me how a quantized KV cache is used during perplexity calculation. Do you have a detailed writeup of how you calculate ppl with the quantized kv cache? Thanks

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