cusolver

NumPy & SciPy for GPU

CUDA Library Samples

Python interface to GPU-powered libraries

A 100x faster SVD for PyTorch⚡️

Hooked CUDA-related dynamic libraries by using automated code generation tools.

Harness the power of GPU acceleration for fusing visual odometry and IMU data with an advanced Unscented Kalman Filter (UKF) implementation. Developed in C++ and utilizing CUDA, cuBLAS, and cuSOLVER, this system offers unparalleled real-time performance in state and covariance estimation for robotics and autonomous system applications.

Bandicoot: C++ library for GPU linear algebra & scientific computing - https://coot.sourceforge.io

Sample CMake template solving Ax=b

A complete example of batched refactorization in cuSOLVER.

Matrix Exponential Approximation using CUDA

test stream of cusolver

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.

Newton's and Halley's Method for the Matrix Polar Decomposition using CUDA

K-means Clustering in CUDA with OpenGL Visualization

matrix operation using gpu

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