Deployment Guide#
Choose the deployment option that best fits your infrastructure and requirements. This guide links to comprehensive deployment documentation for each supported environment.
Choosing Your Deployment
Before you select a deployment guide, consider your infrastructure and requirements:
Public Cloud - Pre-configured environments with NVIDIA-optimized virtual machine instances for rapid deployment, scalability, and pay-as-you-go pricing.
On-Premises Virtualized - Supported using GPU Passthrough and NVIDIA vGPU for Compute. NVIDIA vGPU for Compute enables GPU sharing across multiple virtual machines for multi-tenant environments that require strong isolation and resource optimization.
On-Premises Bare Metal - Direct GPU access for maximum performance, dedicated workloads, high-performance computing, and environments that require full GPU control.
NVIDIA AI Enterprise Deployment Guides#
Deployment |
Deployment Guide |
Description |
|---|---|---|
Public Cloud |
Deploy NVIDIA AI Enterprise on AWS, Azure, Google Cloud, Oracle Cloud, Alibaba Cloud, or Tencent Cloud using NVIDIA-optimized virtual machine instances. |
|
On-Premises: Virtualized Environment |
Deploy NVIDIA AI Enterprise on VMware vSphere with NVIDIA vGPU for Compute, enabling GPU sharing across multiple virtual machines. |
|
On-Premises: Virtualized Environment |
NVIDIA AI Enterprise Red Hat Enterprise Linux With KVM Deployment Guide |
Deploy NVIDIA AI Enterprise on Red Hat Enterprise Linux with KVM hypervisor and NVIDIA vGPU for Compute. |
On-Premises: Virtualized Environment |
NVIDIA AI Enterprise OpenShift on VMware vSphere Deployment Guide |
Deploy NVIDIA AI Enterprise with Red Hat OpenShift Container Platform on VMware vSphere infrastructure. |
On-Premises: Bare Metal Environment |
Deploy NVIDIA AI Enterprise directly on physical servers with dedicated GPU access for maximum performance. |
|
On-Premises: Bare Metal Environment |
NVIDIA AI Enterprise OpenShift on Bare Metal Deployment Guide |
Deploy NVIDIA AI Enterprise with Red Hat OpenShift Container Platform on bare metal servers. |
Multi-Node Deployment |
NVIDIA AI Enterprise Multi-Node Deep Learning Training with TensorFlow |
Set up distributed deep learning training across two vGPU VMs using Docker and TensorFlow. |
Use Cases and Examples#
Deployment Guide |
Description |
|---|---|
NVIDIA AI Enterprise with RAPIDS Accelerator Deployment Guide |
Accelerate Apache Spark 3 data processing and ETL workloads using NVIDIA RAPIDS Accelerator, reducing infrastructure costs and processing time. |
NVIDIA AI Enterprise Natural Language Processing with Triton Inference Server |
Deploy production NLP inference workloads using NVIDIA Triton Inference Server for high-throughput, low-latency text processing. |