Show HN: Flide: Make Jev-like decision models up to 9.5x faster
1 comments
- Points123
- Comments29
–Rank now
#13Peak rank
2Days on list
92Score · 7d
Nov 9, 2026First seen
Rank · 7 days
On Hacker News
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
- Points
- 123
- Comments
- 29
- Submitted by
- unikcc
- Posted
- Nov 9, 2026
- Site
- github.com
Story details from Hacker News ↗ · linked article on github.com.
Trending history
Show HN: Flide: Make Jev-like decision models up to 9.5x faster was first seen on Hacker News · Front page on Nov 9, 2026. Since then it has appeared in 118 checks on 2 different days, across 3 lists (Hacker News · Front page, Hacker News · Show HN, Hacker News · Show HN · this week). Its best position was #13 of 30, reached on Nov 9, 17:09 UTC. It dropped off the list after Nov 10, 16:50 UTC. The same link also trended on GitHub, which raises its cross-platform score.
Rank history
Position on Hacker News · Front page at every check (lower is better).
Last 14 days
Best rank per day (UTC).
13
Oct 28today
Metric history
Platform metric as reported by Hacker News.
Where it trended
| List | Best | Days | Checks | Last seen |
|---|---|---|---|---|
| Hacker News · Front page | #13 | 1 | 43 | |
| Hacker News · Show HN | #1 | 2 | 44 | |
| Hacker News · Show HN · this week | #8 | 2 | 31 | |
| GHGitHub · Rising today omnijev/flide | same link | |||
From the discussion
A few top-level comments from Hacker News, shortened. Read the full thread on Hacker News.
Flide is extremely fast when one input carries many questions, as the shared input is computed only once. Even with a single question, it can still be up to 3x faster, depending on the model size and input length.
You really don't need an entire new inference engine for this. I modified vllm to work just fine for my decision model experiments. It properly uses the single shared context and only recomputes the questions, or if the questions are longer, I let the questions go first and then the context that changes often can go…
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!
Featured in
Archived daily, weekly and monthly lists that include this entry.
Questions
Is Show HN: Flide: Make Jev-like decision models up to 9.5x faster trending on Hacker News right now?
Not at the moment. It was last on the list on Nov 10, 16:50 UTC, after 2 days of trending.
What is the highest rank Show HN: Flide: Make Jev-like decision models up to 9.5x faster reached?
#13 on Hacker News · Front page, on Nov 9, 17:09 UTC. Trendoday checks this list every 15 minutes.
How long has Show HN: Flide: Make Jev-like decision models up to 9.5x faster been trending?
It was first seen on Nov 9, 2026 and has been on the list on 2 days (118 checks) since.
How much discussion did it get on Hacker News?
123 points and 29 comments; submitted by unikcc on Nov 9, 2026.