jevfire

What it is

JEVfire assigns typed variables from finite choices, batching independent fields through vLLM for parallel execution and reuse of their shared instruction/context prefix when the engine cache permits it. Inspired by JEV / RLCD, it uses the pretrained model's existing language-model head to score verified single-token…

The homepage listed on the repository, kikoncuo.github.io, puts it like this: A local Qwen model plays World 1-1 at 71 ms per action on an M4 Max. Explore how JEVfire scores choices, reuses context, and builds typed decisions—with interactive diagrams and open training recipes.

Getting started

From the README:

git clone https://github.com/kikoncuo/jevfire.git
cd jevfire
python -m venv .venv
source .venv/bin/activate

Where the decision sits

jevfire runs its own weights or its own runtime rather than calling a hosted API, so its decisions do not depend on a vendor being up or on a key being funded. The trade is that the model is now yours to keep current.

Models it references: Qwen-2.5-1B-RLCD, Qwen-2.5-1B-RLCD.

How active it is

Created 2026-09-16, last pushed 2026-09-18, 76 stars and 9 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.