Tutel

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

Open-source LLM-based ASR model family for Chinese, dialect, accent, and multilingual speech, with FunASR, vLLM, streaming, and llama.cpp runtimes.

A tiny experimental language designed to be targeted by coding LLMs

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