Projects tagged with “llm-inference”
Browse Jev GitHub projects tagged with llm-inference. Filter, sort and explore their source repositories.
- 422carve-jevOpen-source Jev-like model family with one-token Qwen3.8 decisions, TypeSafe API, one-command setup, and reproducible benchmarks.
FuturixAI-and-Quantum-Works/carve-jev · Python
110ai-agentsbenchmarkclassificationdecision-modeljev-likellm-inferencemodel-family - 518openjevTurn any local LLM into a Jev-style System One decision engine: type-safe answers with raw softmax probabilities. 100% offline, zero API cost.
lookski/openjev · Python
83classificationdecision-modelhugging-facellmllm-inferencelocal-llmsoftmax - 2621kahn1High-throughput, sub-20ms System 1 decision engine on LLM logits. Zero text generation, calibrated probabilities, vLLM prefix caching.
Okura66/kahn1 · Python
00decision-enginefast-inferencellm-inferencepaged-attentionprobability-calibrationpythonqwen2-5 - 2953typedecideOpen-source implementation of the typed-decision pattern popularised by TypeSafe's Jev: read a decision out of a small language model's logits, in the browser. Library, benchmarks and paper. Not affiliated with TypeSafe.
ardada2468/typedecide · Python
00browser-mlconstrained-decodingfine-tuningllm-evaluationllm-inferencelogit-readoutlora
1–4 of 4