Flux is a 100% pure-Julia stack and provides lightweight abstractions on top of Julia's native GPU and AD support. It makes the easy things easy while remaining fully hackable.
Flux has features that sets it apart among ML systems.
Flux provides a single, intuitive way to define models, just like mathematical notation. Julia transparently compiles your code, optimizing kernels for the GPU, for the best performance.
Existing Julia libraries are differentiable and can be incorporated directly into Flux models. Cutting edge models such as Universal Neural Differential Equations are first class, and Zygote enables overhead-free gradients.
GPU kernels can be written directly in Julia via CUDA.jl. Flux is uniquely hackable and any part can be tweaked, from GPU code to custom gradients and layers.
Model-zoo is a collection of demonstrations of the Flux machine learning library. Any of these may freely be used as a starting point for your own models. Metalhead and Flux3D provide trained vision-based and 3D vision-based Flux models, respectively. Furthermore, Transformers provides transformer-based Flux models written in 100% Julia!
Check out Flux's website for more information on the FluxML stack!