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☆92,107Updated this week
- The open-source AI voice studio. Clone, dictate, create.☆55,080Aug 9, 2026Updated last month
- SGLang is a high-performance serving framework for large language models and multimodal models.☆36,140Updated this week
- World's fastest and most advanced password recovery utility☆26,798Updated this week
- Build and run Docker containers leveraging NVIDIA GPUs☆17,599Dec 6, 2023Updated 2 years ago
- Instant neural graphics primitives: lightning fast NeRF and more☆17,553Feb 2, 2026Updated 7 months ago
- Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.☆15,943Updated this week
- kaldi-asr/kaldi is the official location of the Kaldi project.☆15,488Sep 22, 2025Updated 11 months ago
- CUDA on non-NVIDIA GPUs☆14,861Sep 2, 2026Updated 2 weeks ago
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆14,652Updated this week
- Open3D: A Modern Library for 3D Data Processing☆13,978Updated this week
- Solve puzzles. Learn CUDA.☆12,473Sep 1, 2024Updated 2 years ago
- NumPy & SciPy for GPU☆12,328Updated this week
- Open sources book with Modern CUDA Learn Notes for Beginners, includes FP16/BF16, FP8, HGEMM, FlashAttention, CuTe, etc.☆11,979Updated this week
- NumPy aware dynamic Python compiler using LLVM☆11,155Updated this week
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,862Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,453Updated this week
- Containers for machine learning☆9,480Updated this week
- OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.☆9,436Dec 4, 2025Updated 9 months ago
- Samples for CUDA Developers which demonstrates features in CUDA Toolkit☆9,642Sep 9, 2026Updated last week
- A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other ma…☆9,106Updated this week
- Modular ZK(Zero Knowledge) backend accelerated by GPU☆7,649Nov 29, 2024Updated last year
- Go package for computer vision using OpenCV 4 and beyond. Includes support for DNN, CUDA, OpenCV Contrib, and OpenVINO.☆7,502May 28, 2026Updated 3 months ago
- An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.☆7,153Jul 27, 2026Updated last month
- A Python framework for GPU-accelerated simulation, robotics, and machine learning.☆7,127Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,443Updated this week
- A flexible framework of neural networks for deep learning☆5,919Aug 28, 2023Updated 3 years ago
- ALIEN is a CUDA-powered artificial life simulation program.☆5,516Updated this week
- Making it easier to work with shaders☆5,656Updated this week
- A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.☆5,712Updated this week
- Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.☆5,381Aug 17, 2026Updated last month
- A PyTorch Library for Accelerating 3D Deep Learning Research☆5,174Sep 9, 2026Updated last week
- [ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl☆5,001Feb 8, 2024Updated 2 years ago
- ArrayFire: a general purpose GPU library.☆4,902Updated this week
- Optimized primitives for collective multi-GPU communication☆5,096Updated this week
- Fast inference engine for Transformer models☆4,678Aug 31, 2026Updated 2 weeks ago
- Tengine is a lite, high performance, modular inference engine for embedded device☆4,531Mar 6, 2025Updated last year
- Lightning fast C++/CUDA neural network framework☆4,536Apr 21, 2026Updated 4 months ago