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☆43,326Updated this week
- World's fastest and most advanced password recovery utility☆22,303Updated 7 months ago
- Build and run Docker containers leveraging NVIDIA GPUs☆17,342Updated last year
- Instant neural graphics primitives: lightning fast NeRF and more☆16,435Updated 2 months ago
- kaldi-asr/kaldi is the official location of the Kaldi project.☆14,706Updated 2 months ago
- Open3D: A Modern Library for 3D Data Processing☆12,137Updated this week
- CUDA on non-NVIDIA GPUs☆11,056Updated 2 weeks ago
- Solve puzzles. Learn CUDA.☆10,806Updated 7 months ago
- NumPy aware dynamic Python compiler using LLVM☆10,322Updated last week
- NumPy & SciPy for GPU☆10,043Updated this week
- cuDF - GPU DataFrame Library☆8,825Updated this week
- Containers for machine learning☆8,506Updated this week
- A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other ma…☆8,321Updated this week
- Modular ZK(Zero Knowledge) backend accelerated by GPU☆7,774Updated 4 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆12,672Updated this week
- Go package for computer vision using OpenCV 4 and beyond. Includes support for DNN, CUDA, OpenCV Contrib, and OpenVINO.☆6,968Updated this week
- Samples for CUDA Developers which demonstrates features in CUDA Toolkit☆7,220Updated 3 weeks ago
- OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.☆7,732Updated last week
- CUDA Templates for Linear Algebra Subroutines☆7,209Updated last week
- A flexible framework of neural networks for deep learning☆5,909Updated last year
- ALIEN is a CUDA-powered artificial life simulation program.☆5,121Updated this week
- An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.☆5,339Updated 2 weeks ago
- [ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl☆4,960Updated last year
- Tengine is a lite, high performance, modular inference engine for embedded device☆4,455Updated 3 weeks ago
- ArrayFire: a general purpose GPU library.☆4,659Updated this week
- A PyTorch Library for Accelerating 3D Deep Learning Research☆4,686Updated last week
- cuML - RAPIDS Machine Learning Library☆4,582Updated this week
- Lightning fast C++/CUDA neural network framework☆3,941Updated 2 months ago
- Fast inference engine for Transformer models☆3,708Updated this week
- Making it easier to work with shaders☆3,795Updated this week
- LightSeq: A High Performance Library for Sequence Processing and Generation☆3,263Updated last year
- Single C file, Realtime CPU/GPU Profiler with Remote Web Viewer☆3,199Updated 7 months ago
- Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.☆3,136Updated 2 weeks ago
- A GPU-powered real-time analytics storage and query engine.☆3,048Updated 8 months ago
- HeavyDB (formerly OmniSciDB)☆2,976Updated 6 months ago
- A retargetable MLIR-based machine learning compiler and runtime toolkit.☆3,077Updated this week
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,716Updated this week
- Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors☆2,614Updated last year
- A data-parallel functional programming language☆2,493Updated this week