Skip to content

[POC] force kv cache recomputation after each weight update #19

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

Open
wants to merge 1 commit into
base: simulate_conventional_rl
Choose a base branch
from

Conversation

rizar
Copy link
Collaborator

@rizar rizar commented May 12, 2025

This trick to force KV refresh seems to work and is pretty quick to launch. Exploring ATM if this will give us more stable training for our NeurIPS experiment.

@rizar rizar changed the title force kv cache recomputation after each weight update [POC] force kv cache recomputation after each weight update May 17, 2025
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

Successfully merging this pull request may close these issues.

1 participant