A high-throughput and memory-efficient inference and serving engine for LLMs

A PyTorch native platform for training generative AI models

Muon optimizer for neural networks: >30% extra sample efficiency, <3% wallclock overhead

A C++ standalone library for machine learning

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Call Python from NodeJS directly in-process without spawning processes

A Lightweight Pure JavaScript Captcha for Node.js. No C/C++, No ImageMagick, No Canvas.

Fast ML in JS with Bun + Flashlight

oneAPI Deep Neural Network Library (oneDNN)

GPU implementation of a fast generalized ANS (asymmetric numeral system) entropy encoder and decoder, with extensions for lossless compression of numerical and other data types in HPC/ML applications.