Efficient Triton Kernels for LLM Training

🌠 Manage your shell commands.

Tile primitives for speedy kernels

Everything we actually know about the Apple Neural Engine (ANE)

A cross-platform browser ML framework.

Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Simple, modern and fast file watching and code reload in Python.