llm2jev
Any chat model, any engine (SGLang, vLLM, transformers) as a Jev-compatible probability decision service: one prefill, one label token
How it uses Jev
Turn any chat model into a Jev-compatible probability decision service, on SGLang, vLLM, plain transformers or MLX (Apple silicon) , with no model or engine changes.
Getting started
bash pip install llm2jev client + server; the engine runs separately pip install "llm2jev[hf,vision]" + in-process transformers backend (video and audio decoders included) pip install "llm2jev[mlx]" + in-process MLX backend (Apple silicon)
- Languages
- Python 96% · Shell 4%
- License
- MIT
- Latest release
- llm2jev 0.6.1
- Last activity
- Sep 2026
- Added
- 2026-09-24
- Stars at snapshot
- 2
- Status
- Community listing
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.