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.

Sign up for GitHub

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

Jump to bottom

KV Cache with RoPE scaling. #7

Open

murrellb opened this issue Nov 18, 2024 · 0 comments

Member

murrellb commented Nov 18, 2024

Currently RoPE the keys, and cache these. From a 1-minute think, this feels like it won't work with RoPE scaling.

To read:
https://arxiv.org/abs/2309.00071
ggerganov/llama.cpp#2060

AntonOresten mentioned this issue

Use PositionalEmbeddings.jl #14

Closed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment