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☆60,385Updated this week
- World's fastest and most advanced password recovery utility☆24,519Updated last week
- Build and run Docker containers leveraging NVIDIA GPUs☆17,430Updated last year
- SGLang is a fast serving framework for large language models and vision language models.☆18,897Updated last week
- Instant neural graphics primitives: lightning fast NeRF and more☆16,988Updated 2 weeks ago
- kaldi-asr/kaldi is the official location of the Kaldi project.☆15,178Updated last month
- CUDA on non-NVIDIA GPUs☆13,272Updated last week
- Open3D: A Modern Library for 3D Data Processing☆12,881Updated this week
- Burn is a next generation Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.☆13,106Updated last week
- Solve puzzles. Learn CUDA.☆11,569Updated last year
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizati…☆11,880Updated this week
- NumPy aware dynamic Python compiler using LLVM☆10,662Updated last week
- NumPy & SciPy for GPU☆10,543Updated this week
- OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.☆9,363Updated 2 months ago
- cuDF - GPU DataFrame Library☆9,258Updated this week
- Containers for machine learning☆8,871Updated last week
- A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other ma…☆8,619Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆8,603Updated this week
- Samples for CUDA Developers which demonstrates features in CUDA Toolkit☆8,253Updated last month
- Modular ZK(Zero Knowledge) backend accelerated by GPU☆7,744Updated 10 months ago
- Go package for computer vision using OpenCV 4 and beyond. Includes support for DNN, CUDA, OpenCV Contrib, and OpenVINO.☆7,247Updated last month
- 📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉☆8,063Updated this week
- A flexible framework of neural networks for deep learning☆5,906Updated 2 years ago
- An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.☆6,210Updated 2 weeks ago
- A Python framework for accelerated simulation, data generation and spatial computing.☆5,661Updated this week
- ALIEN is a CUDA-powered artificial life simulation program.☆5,257Updated this week
- [ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl☆4,984Updated last year
- cuML - RAPIDS Machine Learning Library☆4,963Updated this week
- A PyTorch Library for Accelerating 3D Deep Learning Research☆4,916Updated last month
- Supercharge Your LLM with the Fastest KV Cache Layer☆5,565Updated this week
- ArrayFire: a general purpose GPU library.☆4,806Updated last month
- Tengine is a lite, high performance, modular inference engine for embedded device☆4,493Updated 7 months ago
- Making it easier to work with shaders☆4,618Updated this week
- Lightning fast C++/CUDA neural network framework☆4,254Updated last week
- HIP: C++ Heterogeneous-Compute Interface for Portability☆4,198Updated this week
- Fast inference engine for Transformer models☆4,070Updated 6 months ago
- FlashInfer: Kernel Library for LLM Serving☆3,911Updated last week
- Simple, scalable AI model deployment on GPU clusters☆3,870Updated this week
- A retargetable MLIR-based machine learning compiler and runtime toolkit.☆3,401Updated this week