CUDA (Compute Unified Device Architecture) is a parallel computing platform and application programming interface (API) model created by NVIDIA for general computing on its own GPUs (Graphics Processing Units). It empowers application developers to leverage the parallel processing capabilities of NVIDIA's GPUs to accelerate computation-heavy tasks, such as matrix operations, physics simulations, deep learning training, and real-time video processing. CUDA provides a C-like programming language that allows developers to write kernel functions, which are executed on the GPU, and manage memory between the host (CPU) and device (GPU) environments. Utilizing CUDA can lead to significant performance improvements in suitable applications, and it integrates well with various programming environments, including Python through libraries like PyCUDA or through frameworks like TensorFlow with GPU support. Understanding basic concepts such as kernels, threads, blocks, and warps is essential for developers to effectively harness the power of GPU programming with CUDA.
View the most prominent open source CUDA projects in the list below. Click on a specific project to view its alternative or complementary packages. Make comparisons and find the best package for your app.
- A high-throughput and memory-efficient inference and serving engine for LLMs☆36,895Updated this week
- World's fastest and most advanced password recovery utility☆21,890Updated 5 months ago
- Build and run Docker containers leveraging NVIDIA GPUs☆17,317Updated last year
- Instant neural graphics primitives: lightning fast NeRF and more☆16,256Updated last week
- kaldi-asr/kaldi is the official location of the Kaldi project.☆14,506Updated last week
- Open3D: A Modern Library for 3D Data Processing☆11,880Updated last week
- CUDA on non-NVIDIA GPUs☆10,573Updated this week
- Solve puzzles. Learn CUDA.☆10,459Updated 5 months ago
- NumPy aware dynamic Python compiler using LLVM☆10,183Updated last week
- NumPy & SciPy for GPU☆9,830Updated this week
- cuDF - GPU DataFrame Library☆8,644Updated this week
- Containers for machine learning☆8,351Updated this week
- A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other ma…☆8,229Updated this week
- Modular ZK(Zero Knowledge) backend accelerated by GPU☆7,772Updated 2 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆8,748Updated this week
- Go package for computer vision using OpenCV 4 and beyond. Includes support for DNN, CUDA, OpenCV Contrib, and OpenVINO.☆6,859Updated 2 weeks ago
- Samples for CUDA Developers which demonstrates features in CUDA Toolkit☆6,864Updated 6 months ago
- OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.☆6,752Updated last week
- CUDA Templates for Linear Algebra Subroutines☆6,165Updated this week
- A flexible framework of neural networks for deep learning☆5,898Updated last year
- ALIEN is a CUDA-powered artificial life simulation program.☆5,067Updated this week
- An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.☆5,107Updated last week
- [ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl☆4,945Updated last year
- Tengine is a lite, high performance, modular inference engine for embedded device☆4,433Updated 4 months ago
- ArrayFire: a general purpose GPU library.☆4,618Updated this week
- A PyTorch Library for Accelerating 3D Deep Learning Research☆4,612Updated this week
- cuML - RAPIDS Machine Learning Library☆4,389Updated this week
- Lightning fast C++/CUDA neural network framework☆3,862Updated last week
- HIP: C++ Heterogeneous-Compute Interface for Portability☆3,872Updated this week
- Fast inference engine for Transformer models☆3,569Updated last month
- Making it easier to work with shaders☆3,564Updated this week
- LightSeq: A High Performance Library for Sequence Processing and Generation☆3,245Updated last year
- Single C file, Realtime CPU/GPU Profiler with Remote Web Viewer☆3,177Updated 5 months ago
- Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.☆3,120Updated last month
- A GPU-powered real-time analytics storage and query engine.☆3,044Updated 6 months ago
- HeavyDB (formerly OmniSciDB)☆2,967Updated 5 months ago
- A retargetable MLIR-based machine learning compiler and runtime toolkit.☆2,965Updated this week
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,665Updated this week
- Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors☆2,557Updated 11 months ago
- A data-parallel functional programming language☆2,460Updated this week