PaddleJitLab/CUDATutorial

A self-learning tutorail for CUDA High Performance Programing.

55
/ 100
Established

This tutorial helps GPU programmers enhance the performance of their applications by teaching advanced CUDA programming techniques. It takes you from setting up a development environment to optimizing complex algorithms like matrix multiplication and convolution. GPU programmers, especially those working with high-performance computing or large language models, would find this project useful to make their code run faster and more efficiently.

911 stars.

Use this if you are a programmer looking to improve the speed and efficiency of your GPU-accelerated applications using CUDA, Triton, or optimizing large language model (LLM) inference.

Not ideal if you are looking for a general introduction to programming or are not working with GPU hardware and accelerated computing.

GPU programming High-performance computing CUDA optimization Parallel computing LLM inference
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

911

Forks

91

Language

JavaScript

License

Apache-2.0

Last pushed

Jan 14, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PaddleJitLab/CUDATutorial"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.