The Julia Programming Language

CUDA programming in Julia.

Forward Mode Automatic Differentiation for Julia

Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods

Geometric Deep Learning for Flux

Computer vision models for Flux

AMD GPU (ROCm) programming in Julia

Graph-based molecule modeling toolkit for cheminformatics

Optimisers.jl defines many standard optimisers and utilities for learning loops.

A Julia wrapper for the NVIDIA Collective Communications Library.

Simple, blazing fast, message-passing graph neural network.

AMDGPU bindings for Flux