AMD GPU (ROCm) programming in Julia

Julia interface to CUBLAS

Fast `StatsBase.countmap` for small types on the GPU via CUDA.jl

CUDA programming in Julia.

A Julia wrapper for the CUDA driver API.

Julia wrapper for CUDA runtime API

Julia wrapper for the NVIDIA cuDNN GPU deep learning library

GPU integrations for Dagger.jl

Reusable array functionality for Julia's various GPU backends.

-

Julia Bindings for the HSA Runtime

Metal programming in Julia

MXNet Julia Package - flexible and efficient deep learning in Julia

OpenCL Julia bindings

Write GPU kernels using pure Julia

Concept for a fast event system, using JIT and GPU acceleration