There are 2 repositories under cuda-library topic.
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
A high performance library for image processing
CUDA Guide
🍒 cuRBLAS (Randomized BLAS) is a GPU-accelerated library for accelerating AI and HPC applications.
Acoustic Vibration of a Fluid in a Three-Dimensional Cavity: Finite Element Method Simulation using CUDA and MATLAB
CUDA Finite Difference Library
CUDA Programming Practices
Library for Event Synchronization and Event Coincidence Analysis
Our participation to the 2025 Gradio Agent MCP Hackathon
A simple image classifier built with Keras using NVIDIA cuda libraries.
A CUDA concurrency library designed to simplify concurrency programming, offering C++-style wrappers for selected CUDA Runtime APIs
A CUDA library of DNA/RNA sequence alignment algorithms.
A beginner's guide to CUDA programming
In this project I have implemented the forward function of a Neural Network composed of sparsely connected layers. In order to parallelize the forward function I have built two implementation: one uses OpenMP and the other uses CUDA.
Cuda Graph Library is a CUDA library that offers a set of parallel graph algorithms.
https://docs.omniverse.nvidia.com/prod_install-guide/prod_install-guide/overview.html
Matrix operation library using single, n-threads or CUDA supported GPU
Awesome GPU Programming
A single header CUDA library that allows logging individual memory accesses of a GPU kernel with as little changes to the code as possible. An export to JSON together with a web-based visualization is included and allows for easy analysis of the memory access patterns.
Price European options written on zero-coupon bonds with Monte Carlo Simulation based on CIR Model
🖼️ CUDA-powered tool for applying box filters to a large amount of images
CUDA library for irregular tasks using a dynamic block-internal balancing mechanism
Retinal Optical Coherence Tomography (OCT) is a non-invasive imaging technique used to capture high-resolution cross-sections of the retina. With over 30 million OCT scans performed annually, efficient analysis is critical for timely diagnosis.