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

optimize generation caching #12

Merged
merged 1 commit into from Nov 3, 2021
Merged

Conversation

neverix
Copy link
Contributor

@neverix neverix commented Nov 3, 2021

Over 10x speedup, adds MLP caching and optimizes attention caching.
Uses changes from the notebook.

Over 10x speedup, adds MLP caching and optimizes attention caching.
Uses changes from https://t.co/BTwo6NKq9H.
@neverix neverix mentioned this pull request Nov 3, 2021
@HetagKoroev
Copy link

HetagKoroev commented Nov 3, 2021

@neverix indeed, the generation rate has increased by more than 10 times. Thanks!

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.

None yet

3 participants