NFNets and Adaptive Gradient Clipping for SGD implemented in PyTorch. Find explanation at tourdeml.github.io/blog/

A Python-level JIT compiler designed to make unmodified PyTorch programs faster.

Quasi Hyperbolic Rectified DEMON Adam/Amsgrad with AdaMod, Gradient Centralization, Lookahead, iterative averaging and decorrelated Weight Decay

optimizer & lr scheduler & loss function collections in PyTorch

Stay Focused. Take a Break.

A modular Wayland compositor library with EGLStreams support

A lightweight compositor for X11

SICP PDF with Texinfo and LaTeX source