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