SCUDA is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.

Matrix multiplication on GPUs for matrices stored on a CPU. Similar to cublasXt, but ported to both NVIDIA and AMD GPUs.

Escoin: Efficient Sparse Convolutional Neural Network Inference on GPUs

Examples showing how to utilize the NVML library for GPU monitoring

A neat C++ custom Matrix class to perform super-fast GPU (or CPU) powered Matrix/Vector computations with minimal code, leveraging the power of cuBLAS where applicable.

Python interface to the NVIDIA CublasXt API

Multiple GEMM operators are constructed with cutlass to support LLM inference.

Several common methods of matrix multiplication are implemented on CPU and Nvidia GPU using C++11 and CUDA.

Cuda NN inference

C++ CUDA-compatible template class that provides an interface for generic purpose matrix related algorithms and computations. Includes Matlab-like functions. This is mainly an example of how to use CUDA code with C++. Don't expect such high performance.

HSD: Hierarchical Spherical Deformation for Cortical Surface Registration

CUDA Gemm Convolution implementation

VTensor, a C++ library, facilitates tensor manipulation on GPUs, emulating the python-numpy style for ease of use. It leverages RMM (RAPIDS Memory Manager) for efficient device memory management. It also supports xtensor for host memory operations.

A really old project that implemented the Stable Fluids using CUDA, cuBLAS and cuSPARSE

Cross platform C/C++ utilities.

Matrix multiplication example performed with OpenMP, OpenACC, BLAS, cuBLABS, and CUDA

GPU linear algebra functions callable from Python

NMF calculations are performed on NVIDIA GPUs using the Cuda API. (GEM released)

Framework, toolkit and ready-to-use applications for numerical linear algebra dependent machine learning algorithms.