matrix operation using gpu

A comparison between single thread program against multi-threading and CUDA approaches

GPU linear algebra functions callable from Python

Matrix Exponential Approximation using CUDA

NumPy-like API accelerated with CUDA

A CUDA approach for computing the multiplication of a transposed matrix with the initial one, using the cuBLAS library.

cuBLAS for pycu_interface.

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

bilibili视频【CUDA 12.x 并行编程入门(Rust版)】配套代码

gpumm - matrix-matrix multiplication by using CUDA, cublas, cublasxt and OpenACC.

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

cuBLAS GEMM Example for FP32 MatMul

cuda、cublas、cublaslt、cusparse...

Library for profiling the execution time of CUDA official library functions

D bindings for CUDA

custom Basic cuBLAS example from modifying NVIDIA cuBLAS Samples

Explore performance implications of various matrix multiplication approaches using GPU/CUDA compared to CPU side processing

Nonnegative matrix factorizations using CUDA

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.