Stars
Code for the Neural GPU model originally described in "Neural GPUs Learn Algorithms"
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
A massively parallel, high-level programming language
Zephyr is a declarative neural network library on top of JAX allowing for easy and fast neural network designing, creation, and manipulation
Massively parallel rigidbody physics simulation on accelerator hardware.
An extremely fast Python linter and code formatter, written in Rust.
A dependency free library of standardized optimization test functions written in pure Python.
RFC document, tooling and other content related to the array API standard
Riemannian Optimization Using JAX
Optax is a gradient processing and optimization library for JAX.
A set of useful perceptually uniform colormaps for plotting scientific data
A lightweight package for generating visually distinct colours.
A project to map out the relations between different equational theories of Magmas.
This package allows macOS Finder to display thumbnails, static QuickLook previews, cover art and metadata for most types of video files.
A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities
Multi-Joint dynamics with Contact. A general purpose physics simulator.
Clean single-file implementation of offline RL algorithms in JAX
(Crafter + NetHack) in JAX. ICML 2024 Spotlight.
Schedule-Free Optimization in PyTorch
Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/
A new markup-based typesetting system that is powerful and easy to learn.
Optimal transport tools implemented with the JAX framework, to solve large scale matching problems of any flavor.