全部项目

kahn1

Okura66/kahn1

High-throughput, sub-20ms System 1 decision engine on LLM logits. Zero text generation, calibrated probabilities, vLLM prefix caching.

SDK 与集成Python
星标
0
派生
0

审查来源

查看引用来源

主题

jevdecision-enginefast-inferencellm-inferencepaged-attentionprobability-calibrationpythonqwen2-5