CUDA C++ Core Libraries
-
Updated
Jun 12, 2024 - C++
CUDA C++ Core Libraries
A performance-oriented prototyping harness for state of the art Molecular Dynamics algorithms
Modeling, inversion and migration focusing on seismic first arrivals
Safe rust wrapper around CUDA toolkit
Cuda learning notebook
A parallel and GPU-accelerated Code for Real-Space All-Electron Linear-Scaling Density Functional Theory
μ-Cuda, COVER THE LAST MILE OF CUDA. With features: intellisense-friendly, structured launch, automatic cuda graph generation and updating.
A General-purpose Parallel and Heterogeneous Task Programming System
Spiral's Machine Learning Library
The "NutBoltClassifier" system represents a significant leap forward in automated fastener classification, harnessing deep learning and computer vision techniques.
This repository provides notes and resources for learning CUDA parallel programming. It includes an overview of GPU architecture, key differences between CPUs and GPUs, and detailed explanations of CUDA concepts and components. Perfect for beginners looking to dive into GPU programming with practical examples and clear explanations.
Thin, unified, C++-flavored wrappers for the CUDA APIs
ThreadPoolManager is a C++ project that implements an efficient multi-threading system using a thread pool for generic functions of the same type and different tasks. It includes task management, synchronization mechanisms, and thread-safe logging to demonstrate concurrent task execution.
TinyChatEngine: On-Device LLM Inference Library
A place where I learn about CUDA
This repo contains CUDA Programming with C++. Projects are done to learn CUDA from scratch.
🎉CUDA 笔记 / 大模型手撕CUDA / C++笔记,更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.
From zero to hero CUDA for accelerating maths and machine learning on GPU.
You're welcome.
Add a description, image, and links to the cuda-programming topic page so that developers can more easily learn about it.
To associate your repository with the cuda-programming topic, visit your repo's landing page and select "manage topics."