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

[WIP] Allow for attention caching during CoCa generation #502

Draft
wants to merge 11 commits into
base: main
Choose a base branch
from

Conversation

sramshetty
Copy link
Contributor

Currently allows for users to set caching argument in model.generate() in order to improve longer generation efficiency. At smaller lengths, the overhead doesn't seem to be worth the cost of caching, but may be an implementation problem.

  • Test speed-up for longer generations
  • If possible, add caching for text encoding

@sramshetty sramshetty marked this pull request as draft April 21, 2023 05:04
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