• Version 471.41
• Sold by NVIDIA

GPU-Accelerated Cloud Gaming

Windows, Windows Server 2019 Base 1803 - 64-bit Amazon Machine Image (AMI)

• Version 21.04.1
• Sold by NVIDIA

The NVIDIA Deep Learning AMI is an optimized environment for running the GPU-optimized deep learning and HPC containers from the NVIDIA NGC Catalog. The deep learning containers on the NGC container registry require this AMI for GPU acceleration on AWS P4D, P3 and G4 GPU instances.

Linux/Unix, Ubuntu Ubuntu 18.04 - 64-bit Amazon Machine Image (AMI)

• Version 470.57
• Sold by NVIDIA

GPU-Accelerated Cloud Gaming

Linux/Unix, Ubuntu 18.04 - 64-bit Amazon Machine Image (AMI)

• Version 446.16
• Sold by NVIDIA

GPU-Accelerated Cloud Gaming

Windows, Windows Server 2016 Base 1803 - 64-bit Amazon Machine Image (AMI)

• Version CloudXR 2.1.29897464 VGPU 12.1
• Sold by NVIDIA

CloudXR is NVIDIA's streaming SDK for delivering virtual reality (VR) and augmented reality (AR) across 5G and Wi-Fi networks. This AMI includes the CloudXR server driver, as well as NVIDIA's RTX Virtual Workstation software.

Windows, Windows Server 2019 Base Windows Server 2019 v 1809 build 17763.1911 - 64-bit Amazon Machine Image (AMI)

• Version 11.2.2
• Sold by NVIDIA

CUDA is a parallel computing platform and programming model that enables dramatic increases in computing performance by harnessing the power of the NVIDIA GPUs.

• Version 21.04.1
• Sold by NVIDIA

This image bundles NVIDIA's container for PyTorch into the NGC base image for AWS.

Linux/Unix, Ubuntu Ubuntu 18.04 - 64-bit Amazon Machine Image (AMI)

• Version 2021.03.10
• Sold by NVIDIA

Amazon EC2 running Microsoft Windows Server is a fast and dependable environment for deploying applications using the Microsoft Web Platform. Amazon EC2 enables you to run any...

Windows, Windows Server 2019 Base 10 - 64-bit Amazon Machine Image (AMI)

• Version 21.06.1
• Sold by NVIDIA

NVIDIA® Triton Inference Server simplifies the deployment of AI models at scale in production and maximizes inference performance. It is an open source inference serving software that lets teams deploy trained AI models from any framework (TensorFlow, TensorRT, PyTorch, ONNX Runtime, OpenVino, or a custom framework), from local or AWS S3 storage and on any GPU- or CPU-based infrastructure in the cloud, data center, or embedded devices.

• Version 5.1
• Sold by NVIDIA

DeepStream SDK delivers a complete streaming analytics toolkit for AI based video and image understanding and multi-sensor processing. DeepStream SDK features hardware-accelerated building blocks, called plugins that bring deep neural networks and other complex processing tasks into a stream processing pipeline.