Top 20 NuGet cuda Packages

ILGPU compiler and runtime library for convenient and high-performance GPU programming in .Net. Samples can be found in the GitHub repository: https://github.com/m4rs-mt/ILGPU.Samples
A complete C# re-write of Berkeley's open source Convolutional Architecture for Fast Feature Encoding (CAFFE) for Windows C# Developers, now with Policy Gradient Reinforcement Learning, cuDNN LSTM Recurrent Learning, and Neural Style Transfer support!
A compiler, runtime, and API for GP-GPU computing using C# or any other NET language, for Windows and Ubuntu x64.
A TensorFlow-inspired neural network library built from scratch in C# 7.3 for .NET Standard 2.0, with GPU support through cuDNN and native memory management
A C# wrapper API of CUDA Driver API (v9.2.88) for Windows and Ubuntu (x64).
Giving Windows C# developers easy access to NVIDIA's CUDA.
Bright Wire CUDA adds GPU support to Bright Wire. This lets you run Bright Wire machine learning on a Maxwell or better NVIDIA GPU.
ILGPU SharpDX library.
TensorSharp is an open source library providing efficient N-dimensional arrays for .NET. Currently, there are backends for running tensor computations on the CPU, and on CUDA GPU hardware. The library is designed to be efficient, easy to install/deploy, and simple to extend. The implementations of m...
This package provides the native DNN dependencies for EMGU TF software libraries
This package provides the native CUDA FFT dependencies for EMGU TF software libraries
Giving Windows C# developers easy access to the Arcade-Learning-Envrionment.
Forked from Surban (https://surban.github.io/managedCuda/), which was forked from Kunzmi (https://kunzmi.github.io/managedCuda/), slightly newer and improved. You must install NVIDIA GPU Toolkit 10.0.130.
This is the .net standard 2 version of BrightWire.CUDA which adds CUDA support to Bright Wire. This lets you run Bright Wire machine learning on a Maxwell or better NVIDIA GPU (x64 only).
Tensor (n-dimensional array) library for F# Core features: - n-dimensional arrays (tensors) in host memory or on CUDA GPUs - element-wise operations (addition, multiplication, absolute value, etc.) - basic linear algebra operations (dot product, SVD decomposition, mat...
managedCuda-wrapper for CUBLAS, only for x64-platform
TensorSharp is an open source library providing efficient N-dimensional arrays for .NET. Currently, there are backends for running tensor computations on the CPU, and on CUDA GPU hardware. The library is designed to be efficient, easy to install/deploy, and simple to extend. The implementations of m...
C# wrapper for CUDA
This package provides the native CUDA dependencies for EMGU.CV-CUDA
Alea GPU Platform compiler. This is a development-only dependency.