The Elegant Machine Learning Stack

Features & Ecosystem

Compiled Eager Code

Flux provides a single, intuitive way to define models, just like mathematical notation. Julia transparently compiles your code, optimising and fusing kernels for the GPU, for the best performance.

Differentiable Programming

Existing Julia libraries are differentiable and can be incorporated directly into Flux models. Cutting edge models such as Neural ODEs are first class, and Zygote enables overhead-free gradients.

First-class GPU support

GPU kernels can be written directly in Julia via CUDAnative. Flux is uniquely hackable and any part can be tweaked, from GPU code to custom gradients and layers.

The Model Zoo

A rich collection of Flux scripts to learn from, or tweak to your own data. Trained Flux models can be used from TextAnalysis or Metalhead.


Import trained ONNX models as Flux scripts, for high-quality inference or for transfer learning.


Export your models to JavaScript for the browser, or see our experiments page for demos.

Probabalistic Programming

The Turing.jl and Stheno libraries enables probabalistic programming, bayesian inference and Gaussian processes on top of Flux.

TPUs & Colab

Flux models can be compiled to TPUs for cloud supercomputing, and run from Google Colab notebooks.

Publications Highlights

Policy Guided Monte Carlo: Reinforcement Learning Markov Chain Dynamics

We introduce Policy Guided Monte Carlo (PGMC), a computational framework using reinforcement learning to improve Markov chain Monte Carlo (MCMC) sampling. arXiv

Machine Learning and System Identification for Estimation in Physical Systems

We draw inspiration from both classical system identification and modern machine learning in order to solve estimation problems for real-world, physical systems. link

Don't Unroll Adjoint: Differentiating SSA-Form Programs

This paper presents reverse-mode algorithmic differentiation (AD) based on source code transformation, in particular of the Static Single Assignment (SSA) form used by modern compilers. arXiv

Automatic Full Compilation of Julia Programs and ML Models to Cloud TPUs

We describe a method and implementation for offloading suitable sections of Julia programs to TPUs via the Google XLA compiler. arXiv


Simulating the Motion of Charged Bodies

JSoC Cohort

Differentiable Control Problems

What Is Differentiable Programming?

Researchers, users and developers of Flux