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

Llama 3 ring attention implementation for inference #21

Open
joshpopelka20gmail opened this issue Jul 25, 2024 · 1 comment
Open

Llama 3 ring attention implementation for inference #21

joshpopelka20gmail opened this issue Jul 25, 2024 · 1 comment

Comments

@joshpopelka20gmail
Copy link

Hope you can help with this. I'm trying to implement ring attention using Llama 3 architecture and I'm starting with the blockwise parallel transformer piece. My question is when do I start to break the input sequence into chunks 1) after projection of weights to Q, K, and V or 2) prior to self-attention in the block?

Any feedback would be much appreciated :)

@haoliuhl
Copy link
Owner

haoliuhl commented Aug 4, 2024

Hi, ringattention inference has been supported in LWM

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