Jev GPU

A frozen decision server that serves Gemma 4 31B — quantized to FP8 at startup — in TypeSafe's /v1/systemone format, reading the next-token distribution instead of generating tokens. It needs one FP8 NVIDIA GPU with 80 GB and has no authentication.

Serves DiffusionGemma-Jev behind a TypeSafe-compatible API on Google Cloud Run with an NVIDIA RTX PRO 6000 GPU, built on mmastrac/djev. Cold start is about 47.5 s and the median server response 61 ms; it exposes /v1/systemone plus snake, dino and tetris demos.

A local-inference walkthrough that compares Kev, SemIf, Von, and OpenJev on consumer hardware, including Brier scores and a fake-probabilities warning.