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☆52,204Updated this week
- World's fastest and most advanced password recovery utility☆23,034Updated this week
- Build and run Docker containers leveraging NVIDIA GPUs☆17,400Updated last year
- Instant neural graphics primitives: lightning fast NeRF and more☆16,780Updated last week
- kaldi-asr/kaldi is the official location of the Kaldi project.☆14,985Updated 2 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆16,097Updated this week
- Open3D: A Modern Library for 3D Data Processing☆12,537Updated last week
- CUDA on non-NVIDIA GPUs☆12,689Updated this week
- Burn is a next generation Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.☆11,604Updated this week
- Solve puzzles. Learn CUDA.☆11,279Updated 10 months ago
- NumPy aware dynamic Python compiler using LLVM☆10,522Updated 2 weeks ago
- NumPy & SciPy for GPU☆10,336Updated last week
- cuDF - GPU DataFrame Library☆9,044Updated this week
- Containers for machine learning☆8,715Updated this week
- OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.☆9,355Updated last week
- A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other ma…☆8,470Updated this week
- Modular ZK(Zero Knowledge) backend accelerated by GPU☆7,763Updated 7 months ago
- CUDA Templates for Linear Algebra Subroutines☆7,941Updated last week
- Samples for CUDA Developers which demonstrates features in CUDA Toolkit☆7,761Updated last month
- Go package for computer vision using OpenCV 4 and beyond. Includes support for DNN, CUDA, OpenCV Contrib, and OpenVINO.☆7,141Updated last week
- A flexible framework of neural networks for deep learning☆5,911Updated last year
- An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.☆5,728Updated last week
- ALIEN is a CUDA-powered artificial life simulation program.☆5,202Updated this week
- A Python framework for accelerated simulation, data generation and spatial computing.☆5,299Updated this week
- [ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl☆4,981Updated last year
- A PyTorch Library for Accelerating 3D Deep Learning Research☆4,834Updated last week
- cuML - RAPIDS Machine Learning Library☆4,823Updated this week
- ArrayFire: a general purpose GPU library.☆4,740Updated this week
- Tengine is a lite, high performance, modular inference engine for embedded device☆4,478Updated 4 months ago
- Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.☆4,526Updated this week
- 📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉☆5,542Updated this week
- Lightning fast C++/CUDA neural network framework☆4,125Updated last week
- HIP: C++ Heterogeneous-Compute Interface for Portability☆4,121Updated this week
- Making it easier to work with shaders☆4,277Updated this week
- Fast inference engine for Transformer models☆3,911Updated 3 months ago
- LightSeq: A High Performance Library for Sequence Processing and Generation☆3,282Updated 2 years ago
- Single C file, Realtime CPU/GPU Profiler with Remote Web Viewer☆3,247Updated 10 months ago
- Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.☆3,187Updated this week
- A retargetable MLIR-based machine learning compiler and runtime toolkit.☆3,220Updated this week
- A GPU-powered real-time analytics storage and query engine.☆3,059Updated last year