NVIDIA Holoscan
Accelerate edge AI development by getting sensor data to the GPU for real-time inference—at the edge or in the cloud.
Moon Surgical
Overview
What is NVIDIA Holoscan?
Holoscan is a multimodal computing platform that delivers the accelerated, full-stack infrastructure you need for scalable, software-defined, and real-time processing of streaming data running at the edge.
Software-Defined Hardware
Get to know the Holoscan Platform
The Holoscan platform spans hardware and software components that bridge sensors with edge servers, networking, on-premises data centers, and cloud computing with optimized libraries, tools, and containers for data processing. It also includes template applications to facilitate rapid prototyping, sample AI models for jump-starting training, and core microservices to run streaming, imaging, and other applications.
Benefits
Real-Time Sensor Processing for Seamless EDGE AI Solutions
Low-Latency, Real-Time Performance
Get optimized performance for ultra-low-latency processing of high-throughput sensor data (video, audio, ultrasound, etc.), enabling fast AI inference and immediate decision-making.
Modular Pipeline Architecture
Using a graph-based SDK with plug-and-play operators for I/O, preprocessing, inference, postprocessing, and visualization lets you build flexible, reusable pipelines in Python or C++, speeding up development and experimentation.
Edge-to-Cloud Scalability
Run the same pipeline across the full range of target devices—from NVIDIA Jetson™ (embedded) to IGX (industrial edge) to the NVIDIA AGX™ (data center)—without rewriting your code. Holoscan abstracts the hardware while maximizing GPU acceleration.
Built-In Ecosystem Integrations
Integrate key tools and libraries like NVIDIA® GPUDirect® for fast I/O, NVIDIA Triton™ Inference Server for AI, and NVIDIA MONAI for medical imaging. This saves time and avoids stitching together disparate systems.
Use Cases
Transforming Industries with Real-Time Edge AI
Holoscan enables cutting-edge AI solutions—from medical devices to healthcare, robotics, and scientific computing.
-
Medical Devices
-
Healthcare Robotics
-
Scientific Computing
Medical Devices
Holoscan provides real-time edge AI capabilities for medical device developers. Companies can now explore new AI-powered capabilities, accelerate time to market, and lower development and maintenance costs for medical-grade devices.
Atlas Meditech
Healthcare Robotics
Virtual Incision used the NVIDIA Holoscan platform to power its miniaturized surgical robot, MIRA, achieving low-latency, high-performance AI pipelines for real-time control and visualization. By using the Holoscan SDK, sensor bridge, NVIDIA® CUDA®, and IGX Orin with 6000 NVIDIA Ada GPUs, they cut system latency by 3x, enabling smoother robotic response and enhanced surgical workflow. NVIDIA Isaac Sim™ also supports virtual testing and synthetic data generation to accelerate AI skill development in simulation, ensuring reliability and efficiency in minimally invasive procedures.
Virtual Incision
Scientific Computing 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.
SETI Institute
Starting Options
Ready to Get Started?
Next Steps