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

Evaluate Profile-Guided Optimization (PGO) performance benefits for the library #103

Open
zamazan4ik opened this issue Apr 11, 2024 · 0 comments

Comments

@zamazan4ik
Copy link

zamazan4ik commented Apr 11, 2024

Hi!

Profile-Guided Optimization (PGO) is a compiler optimization technique that allows optimize an application based on runtime statistics like frequently executed branches for making better optimization decisions like inlining. I checked PGO optimization opportunities for different kinds of software - all results are available at https://github.com/zamazan4ik/awesome-pgo .

I already did some benchmarks for HuggingFace Tokenizers with PGO with some positive results. I think you could be interested in it.

In this issue, I suggest performing some PGO benchmarks for the rust-tokenizers library. If PGO shows positive effects on the library performance - it could be a good idea to write a note about PGO in the README file at least. Maybe some CPU parts of https://github.com/guillaume-be/rust-bert also can be optimized with PGO.

Please don't consider the issue as a bug - it's just a performance improvement idea.

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

No branches or pull requests

1 participant