# NVIDIA CUDA Toolkit

The NVIDIA® CUDA® Toolkit provides a development environment for creating high-performance, GPU-accelerated applications. With it, you can develop, optimize, and deploy your applications on GPU-accelerated embedded systems, desktop workstations, enterprise data centers, cloud-based platforms, and supercomputers. The toolkit includes [GPU-accelerated libraries](https://developer.nvidia.com/cuda/cuda-x-libraries), debugging and optimization tools, a C/C++ compiler, and a runtime library.

[Download Now](https://developer.nvidia.com/cuda-downloads)

* * *

## CUDA Features

### CUDA Tile: A New Era of GPU Programming

NVIDIA CUDA Tile is a tile-based GPU programming model based on the foundation of the CUDA Tile IR specification and tools including cuTile.

[Learn More About CUDA Tile](https://developer.nvidia.com/blog/focus-on-your-algorithm-nvidia-cuda-tile-handles-the-hardware)

### New Release, New Benefits

CUDA 13.2 enhances GPU kernel development by extending CUDA Tile support to Ampere and Ada architectures, introducing new constructs such as closures and recursion into cuTile Python, and unifying the ARM ecosystem into a single CUDA toolkit for seamless deployment from data center to edge.

[Learn More About CUDA Toolkit 13.2](https://developer.nvidia.com/blog/cuda-13-2-introduces-enhanced-cuda-tile-support-and-new-python-features/)

### Tile Programming in Python

cuTile Python is an expression of the CUDA Tile programming model in Python. It is built on top of the CUDA Tile IR specification and allows you to write tile kernels in Python.

[Learn More About cuTile Python](https://developer.nvidia.com/blog/simplify-gpu-programming-with-nvidia-cuda-tile-in-python)

## Tutorials

Explore essential video tutorials covering CUDA Toolkit installation on Windows and WSL, ensuring compatibility, upgrading Jetson™ devices, and optimizing applications through profiling and debugging.

### Accelerating Applications with Parallel Algorithms | CUDA C++ Class Part 1

[Watch Video (2:05:26)](https://www.youtube.com/watch?v=H3AQnlpxk0c)

### CUDA Tutorials - Simplifying CUDA Upgrades for Jetson Devices

[Watch Video (19:05)](https://www.youtube.com/watch?v=_JgNA82325I)

### CUDA Tutorials I Profiling and Debugging Applications

[Watch Video (10:30)](https://www.youtube.com/watch?v=dB5Jxwj0PDw)

### CUDA Tutorials I Installing CUDA Toolkit on Windows and WSL

[Watch Video (2:56)](https://www.youtube.com/watch?v=JaHVsZa2jTc)

## GTC Digital Webinars

Dive deeper into the latest CUDA features.

### What’s CUDA All About Anyway?

[Watch Now](https://www.nvidia.com/en-us/on-demand/session/gtc25-S72571/)

### CUDA—New Features and Beyond

[Watch Now](https://www.nvidia.com/en-us/on-demand/session/gtc25-s72383/)

### How to Write a CUDA Program: The Parallel Programming Edition

[Watch Now](https://www.nvidia.com/en-us/on-demand/session/gtc25-s72897/)

## Customer Stories

See how developers, scientists, and researchers are using CUDA today.

### Developer Spotlight: Using HPC to Explore the Universe

Wes Armour, director at the Oxford e-Research Centre, discusses the role of GPUs in processing large amounts of astronomical data collected by the Square Kilometre Array and how CUDA is the best-suited option for their signal processing software.

[Watch Video (1:47)](https://www.youtube.com/watch?v=Oz0aeL6dQGs&t=107s)

### Developer Spotlight: Opening a New Era of Drug Discovery with Amber

David Cerutti and Taisung Lee from Rutgers University share how Amber, harnessing CUDA, is advancing multiple scientific domains and opening a new era of drug discovery and design.

[Watch Video (2:02)](https://www.youtube.com/watch?v=FqnPGHdh7iM)

### Developer Spotlight: Visualizing and Simulating Atomic Structures

John Stone, senior research programmer at the Beckman Institute at the University of Illinois, Urbana-Champaign, discusses how CUDA and GPUs are used to process large datasets to visualize and simulate high-resolution atomic structures.

[Watch Video (2:15)](https://www.youtube.com/watch?v=DWWXaUNVZM4)

## Featured Blogs

#### Build with DeepSeek V4 Using NVIDIA Blackwell and GPU-Accelerated Endpoints

DeepSeek just launched its fourth generation of flagship models with DeepSeek-V4-Pro and DeepSeek-V4-Flash, both targeted at enabling highly efficient million-token context inference. [Read more](https://developer.nvidia.com/blog/build-with-deepseek-v4-using-nvidia-blackwell-and-gpu-accelerated-endpoints/)

#### Federated Learning Without the Refactoring Overhead Using NVIDIA FLARE

The latest version … [Read more](https://developer.nvidia.com/blog/federated-learning-without-the-refactoring-overhead-using-nvidia-flare/)

#### Winning a Kaggle Competition with Generative AI–Assisted Coding

In March 2026, … [Read more](https://developer.nvidia.com/blog/winning-a-kaggle-competition-with-generative-ai-assisted-coding/)

#### Simplify Sparse Deep Learning with Universal Sparse Tensor in nvmath-python

We’re excited to announce the integration of the UST into nvmath-python v0.9.0 [Read more](https://developer.nvidia.com/blog/simplify-sparse-deep-learning-with-universal-sparse-tensor-in-nvmath-python/)