NVIDIA AI Enterprise Deployment Guide

This deployment guide provides the technical framework for implementing the co-engineered Red Hat AI Factory with NVIDIA solution, detailing the integration of NVIDIA AI Enterprise software and Red Hat OpenShift AI across hardware, networking, and software installation, from initial setup to deploying and experimenting with NVIDIA NIM microservices.

NVIDIA AI Enterprise

• Platform Overview
  • Application Layer
    • Application Layer Software
  • Infrastructure Layer
    • Infrastructure Layer Software
    • Infra Software Branch Support Matrix
    • Infra Software Branch Release Notes

Deployment Guide

• Red Hat AI Factory with NVIDIA Overview
• Prerequisites
  • Hardware Requirements
    • Compute
    • Networking
    • Storage
• Software Overview
  • NVIDIA AI Enterprise
  • Red Hat AI Enterprise
    • Red Hat OpenShift
    • Red Hat OpenShift AI
• Install the Node Feature Discovery (NFD) Operator
  • Verifying NFD node labels using the web console
  • Verifying NFD node labels using the CLI
• Install NVIDIA Network Operator (Optional)
  • Verify presence of NVIDIA Networking Devices
• Install the NVIDIA GPU Operator
  • Verify availability of GPU resources
• Deploying AI workloads with the NIM Operator on Red Hat OpenShift
  • Standalone Deployments
  • Deploy with Kserve
• Deploying NVIDIA NIM with Red Hat OpenShift AI
  • Experiment with NVIDIA NIM in the Playground in the GenAI Studio in Red Hat OpenShift AI
    • Enable the Playground feature in Gen AI studio
    • Update Dashboard Configuration
    • Enable Llama Stack Operator
    • Labeling Models as Gen AI Assets
    • Labeling Existing Models
    • Troubleshooting
  • Starting the Playground and Prompting NIM
    • Access the Playground
    • Configure the Chat Session
• Next Steps
• Additonal Resources

Support

• Support and Services
  • How to Get Support

Notices

• Notices
  • Notice
  • Trademarks
  • Copyright