#cuda-programming Repositories
Discover 33 active open source GitHub repositories tagged with #cuda-programming, accumulating 74,529 total stars (averaging 2,258 stars per project). Leading this topic is taskflow/taskflow with 12,246 stars.
33 repositories total
Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
Official PyTorch implementation of One-Minute Video Generation with Test-Time Training
Official code for the paper "LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes".
[CVPR 2025] Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering
A 120-day CUDA learning plan covering daily concepts, exercises, pitfalls, and references (including โProgramming Massively Parallel Processorsโ). Features six capstone projects to solidify GPU parallel programming, memory management, and performance optimization skills.
LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.
A project related to computer vision, machine learning, and deep learning, including course notes and self-developed programs.
Frequently Asked Questions
What is the most popular #cuda-programming repository on GitHub?
The top ranked open source #cuda-programming project on GitHub is taskflow/taskflow with 12,246 stars. A General-purpose Task-parallel Programming System in C++
Which programming languages are most used in #cuda-programming repositories?
Among the top ranked #cuda-programming projects on GitHub, the most common programming languages are Cuda, C++, Python, Jupyter Notebook.
How is the #cuda-programming repository ranking calculated?
We track 33 active open source repositories tagged with #cuda-programming (500+ stars), totaling 74,529 stars with an average of 2,258 stars per repository. Rankings update daily from the GitHub API.