kimi-k3-in-c

The most atomic way to train and inference a GPT in pure, dependency-free C

Run a 1-billion parameter LLM on a $10 board with 256MB RAM

Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4

A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.