logoalt Hacker News

Show HN: Flide: Make Jev-like decision models up to 9.5x faster

5 points • by unikcc • today at 4:43 AM • 1 comment • view on HN

Decision models need their own inference engine.

So we developed Flide, a high-performance and exact inference engine for Jev-like decision models.

Flide achieves up to a 9.5x speedup over vLLM and SGLang.

It now supports 30+ popular local Jev-like decision models.

Start to make your decision immediately:

pip install flide

Comments

unikcc • today at 4:55 AM

Hi HN! I'm one of the Flide team.

We built Flide from scratch to make Jev-like decision model inference up to 9.5x faster than vLLM and SGLang, while keeping exactness.

Here is the source code: https://github.com/OmniJev/Flide

Look forward to hearing your feedback and ideas!