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

[zamazan4ik]

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.