Yinsongxu/LLM2Jev

[](pyproject.toml) [](LICENSE) [](docs/en/usage.md) [](docs/en/usage.md) Project website · 简体中文 Turn your LLM / MLLM into a Jev-style decision model. Zero training required. Put your existing model weights to work on classification, scoring, and action selection from text and images. Get decision probabilities with prefill alone, across SGLang, Transformers, and MLX backends. Call decisions and chat through the same client, built on the OpenAI Python SDK, wherever the serving backend supports both. Earlier updates Candidates share state, and candidates for the same question also share its instructions. The SGLang backend first scores a real criteria candidate to establish the prefix cache, then submits candidates that can reuse it. Each candidate is scored once, reducing repeated computation for long inputs with many candidates. The MLX backend explicitly prefills shared prefixes before scoring candidate suffixes. Both backends preserve the same binary scoring interface. See the Usage guide for details. Learn how it works: From…