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

Added support for Medusa speculative decoding adapters #372

Merged
merged 48 commits into from
Apr 3, 2024
Merged

Conversation

tgaddair
Copy link
Contributor

@tgaddair tgaddair commented Apr 2, 2024

This PR adds support for using a Medusa adapter as a static adapter provided during initialization. Does not yet support using different Medusa adapters per request. In the current behavior, once LoRAX has been initialized with Medusa, any request (with or without another LoRA adapter) will have the speculative decoding applied.

In following PRs, we will add support for other speculative decoding methods like ngram speculation.

Related #205.
Related #259.
Related #329.

@tgaddair tgaddair merged commit 5581ee8 into main Apr 3, 2024
2 checks passed
@tgaddair tgaddair deleted the medusa branch April 3, 2024 17:27
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