NVIDIA Holoscan

NVIDIA Holoscan accelerates edge AI development by getting sensor data to the GPU for real-time inference.

Get to know the Holoscan Platform

Holoscan SDK

Start building end-to-end sensor-processing pipelines with your application framework. Holoscan streamlines these pipelines with high-performance, user-friendly programming options and production readiness. It features seamless I/O integration, bring-your-own (BYO) sensor, AI model inference, and model capabilities.



Holoscan Sensor Bridge

Integrate heterogeneous sensor data seamlessly with Holoscan Sensor Bridge, which provides a critical link between high-throughput sensor data and the GPU. It standardizes and manages data ingestion from a variety of sensor interfaces—like camera feeds, ultrasound, or endoscopic video—ensuring low-latency, synchronized, and reliable transfer of data for real-time AI processing.



NVIDIA IGX ORIN

Deploy on production-ready hardware with the NVIDIA IGX Orin, an industrial-grade platform that combines enterprise-level hardware, software, and support. While Holoscan SDK offers flexibility in deployment on your target device, IGX allows companies to focus on application development and realize the benefits of AI faster.



Real World Examples

NVIDIA Holoscan for Medical Devices

Holoscan provides real-time edge AI capabilities for medical device developers. It allows companies in the medical device industry to explore new AI-powered capabilities, accelerate time to market, and lower development and maintenance costs for medical-grade devices.


Learn More

Atlas Meditech

NVIDIA Holoscan for HPC at the Edge

Holoscan is a universal sensor processing platform, purpose-built for high performance while meeting the size, weight, and power (SWaP) constraints at the edge. It delivers a flexible software stack across a common high-performance hardware and software platform to accelerate data analysis and visualization workflows at the edge.


Learn More

Download the NVIDIA Holoscan SDK

To compile the open-source Holoscan SDK yourself, download it from GitHub.


PyPi

Pip Install NVIDIA Holoscan SDK

Ubuntu Package

Download and install the Debian Package

NGC Container

Run within the Holoscan Container

Conda

Now available on Conda

Holoscan Reference Applications

Access an open repository of Holoscan reference applications and operators, including prebuilt examples of end-to-end applications and guidance on how to use, customize, and scale them.

Multi-AI AR-Assisted Surgery

Reference Application: End-to-End Surgical Video

NVIDIA Holoscan’s Surgical Video Workflow enables rapid, low-latency processing of surgical video feeds with advanced AI models for tool detection and segmentation. With a modular, customizable pipeline, it’s designed to streamline the development of AI-driven medical imaging solutions.

Get Started
3D Slicer With NVIDIA Holoscan Image credit: OpenIGTLink

OpenIGTLink

Real-Time Visualization With 3D Slicer

This reference application enables images to be easily sent from 3D Slicer to Holoscan for running medical AI inference at the edge for guiding surgical planning, medical research, and advanced diagnostics—leveraging the strength of both platforms within a single reference application.

Learn More About Using 3D Slicer With Holoscan on GitHub
Volume Rendering With NVIDIA Holoscan Image credit: Magic Leap

IMagic Leap

XR: Volume Rendering

The XR Volume Rendering application combines Holoscan’s real-time AI processing with Magic Leap’s AR display and spatial tracking, showing how XR in medical imaging can help with surgical planning, medical education, and patient consultations.

Learn More About Volume Rendering With Holoscan on GitHub

FAQ

NVIDIA Holoscan is a domain-agnostic AI computing platform that delivers the accelerated, full-stack infrastructure required for scalable, software-defined, and real-time processing of streaming data running at the edge or in the cloud.

It spans hardware and software components that bridge sensors with edge servers, networking, on-premises data centers, and cloud computing with optimized libraries, tools, containers for data processing, as well as template applications to facilitate rapid prototyping, sample AI models for jump-starting training, and core microservices to run streaming, imaging, and other applications.


The Clara AGX and NVIDIA IGX Orin Developer Kits are Arm-based.



The Clara AGX Developer Kit is the predecessor of the updated NVIDIA IGX Orin Developer Kit. Read more about our devkits.


Clara AGX Developer Kit NVIDIA IGX Orin Developer Kit
Availability Now Q2 2023
SoC NVIDIA Jetson AGX Xavier™ NVIDIA Jetson™ AGX Orin
Discrete GPU (dGPU) NVIDIA RTX™ 6000 NVIDIA RTX A6000
SmartNIC NVIDIA ConnectX-6® NVIDIA ConnectX-7®
Networking Bandwidth 100 GbE / 10 GbE / 1 GbE 2x 100 GbE / 2x 1GbE
SSD 250GB 500GB

Developer Blogs

Learn about solutions for developers.

Join NVIDIA Developer Program