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

Support for quantized KV Cache #5

Open
zjnyly opened this issue Jan 8, 2025 · 1 comment
Open

Support for quantized KV Cache #5

zjnyly opened this issue Jan 8, 2025 · 1 comment

Comments

@zjnyly
Copy link

zjnyly commented Jan 8, 2025

Hi, have you tested the performance on quantized KV Cache? Is it possible to keep a resonable high performance under int8 quantization?

@dreaming-panda
Copy link
Contributor

I evaluated INT8 quanto. The accuracy is good (on Llama3.1-8B). But I currently do not have the bandwidth to implement this on the CPU (actually, I do not know how to do this except by calling quanto, which is not very fast on the CPU).

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

2 participants