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

Speedup ffn and gelu #15

Draft
wants to merge 3 commits into
base: main
Choose a base branch
from
Draft

Speedup ffn and gelu #15

wants to merge 3 commits into from

Conversation

certik
Copy link
Owner

@certik certik commented Mar 8, 2023

On my machine these changes speedup inference from 0.789s to 0.602s.

certik added 3 commits March 7, 2023 15:47
This provides about 4% speedup from 0.789 to 0.758s.
This provides about 20% speedup from 0.752s to 0.602s.
@certik
Copy link
Owner Author

certik commented Mar 17, 2023

With caching on, both main and this PR show 0.288s. With caching off, this PR is 0.543s, main is 0.716s.

@certik certik marked this pull request as draft March 17, 2023 15:20
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.

2 participants