wfzyx/von

An Open-Source, Non-Autoregressive System One Decision Model. Calibrated discrete, probabilistic, and ordinal inference in sub-25ms. [](https://huggingface.co/wfzyx/von-1.0) [](https://opensource.org/licenses/Apache-2.0) [](https://www.python.org/) [](https://www.typescriptlang.org/) Autoregressive large language models (LLMs) decode token-by-token to perform classification, intent routing, and guardrail validation. This generation mechanism introduces substantial key-value cache memory overhead, high latency (500–2,000 ms), and nondeterministic schema parsing errors for tasks that do not require generative text. Von implements the System One computational paradigm: reflexive, parallel, deterministic, and statistically calibrated decision-making. Operating entirely in-process or via an HTTP server, Von evaluates arbitrary discrete and continuous criteria directly over input state in a single forward pass without autoregressive text generation. Von is evaluated across two independent empirical suites: Von leads all open local System One models on the 49-task v2 suite at 71.5% macro (Choice routing at 83.4%, with symptom triage at 100.0%, home services at 95.7%, and city routing at 94.7%), while outperforming closed-source Jev by +66.9%…