Jev Llama Cpp

A Java and Python implementation of parallel constrained decoding: fill a whole JSON schema of booleans and enums in two forward passes, with calibrated confidence per field and output that is schema-valid by construction.

An independent reimplementation of the OpenJev mechanism on PrismML's 1.75-bit Bonsai weights: typed decisions read straight off the next-token distribution of a 5.95 GB 27B model in one forward pass.

ggml's announcement that llama.cpp server supports decision models through a /v1/systemone endpoint: send a state and typed questions, get a probability per option from one forward pass. It lists six GGUF decision models from Julia-1 (144M) to OpenJev (27B) with single-question latencies.