Break Through the Barriers to AI Speed and Scale
Experience the AI performance of NVIDIA DGX-2™, the world’s first 2 petaFLOPS system integrating 16 NVIDIA V100 Tensor Core GPUs for large-scale AI projects. Powered by NVIDIA DGX software and the scalable architecture of NVIDIA® NVSwitch™, DGX-2 can take on your complex AI challenges.
NVIDIA DGX-2 integrates 16 NVIDIA V100 Tensor Core GPUs, so you can work with the biggest training datasets.
The NVSwitch networking fabric enables greater model parallelism with 2.4 terabytes per second (TB/s) of bisection bandwidth, delivering a 24X increase over prior generations.
Build your own private enterprise-grade AI cloud with virtualization support and an architecture purpose-built for scaling.
NVIDIA DGXperts are a global team of 14,000+ AI-fluent professionals who have built a wealth of experience over the last decade to help you maximize the value of your DGX investment.
NVIDIA DGX-2 Delivers 195X Faster Deep Learning Training
Workload: ResNet-50, BS=256, 90 epochs to solution | CPU: dual Xeon Platinum 8180 | DGX-1 GPU: 8X NVIDIA Tesla V100 32GB | DGX-2 GPU: 16X NVIDIA Tesla V100 32GB
Red Hat Enterprise Linux is supported on NVIDIA DGX Systems
The German Research Center for Artificial Intelligence (DFKI) is using increased GPU memory and fully connected GPUs based on the NVSwitch architecture in NVIDIA DGX-2 to analyze large-scale satellite and aerial imagery and efficiently dispatch emergency resources.
Oregon State University (OSU) uses NVIDIA DGX-2 to accelerate their work in AI, robotics, driverless vehicles, medical imaging, and other research areas.
NVIDIA DGX-2’s large memory and massive computing power enable specialists to tackle training of large, 3D datasets in minutes instead of days, while keeping the data secure through a federated learning infrastructure.
The Inception Institute of Artificial Intelligence (IIAI) is using NVIDIA DGX-2 to help researchers and engineers accelerate AI research in smart cities and medical imaging.
Learn about enterprise-grade support for NVIDIA DGX systems.
Leadership-Class AI Infrastructure
Thank you for your submission.
THANK YOU FOR CONTACTING USThank you for your interest in NVIDIA DGX.A representative will follow up soon with more information.
NVIDIA Privacy Policy
DGX-2 systems are used for workloads that involve large models, more complex networks, and data and model parallelism, including high-definition video training and natural language processing (NLP).
The DGX Operating System (DGX OS) already includes necessary packages, drivers, and other configurations. The catalog of NVIDIA-optimized deep learning software containers is free to everyone through NGC™.
For information on how to deploy, manage, and monitor a multi-node DGX cluster, refer to our user guide.