From AI Data to GPU Inference: OpenNebula, NetApp, and NVIDIA in Action

Deploying AI inference services requires more than GPU capacity. Organizations need persistent access to AI models and datasets, flexible GPU infrastructure, and the ability to deploy and scale workloads without complex provisioning or unnecessary data movement.

Join OpenNebula and NetApp for a live demonstration of how OpenNebula, NetApp ONTAP, and NVIDIA technologies work together to deliver an integrated, open, and scalable platform for AI inference.

Discover how to keep AI models and datasets securely stored in NetApp ONTAP while using OpenNebula to provision GPU-powered Kubernetes environments on demand. See how NVIDIA technologies enable AI inference services that can be deployed and scaled in minutes, while maintaining isolation between tenants and control over infrastructure and data.

What You’ll See:

• An Integrated AI Architecture: How OpenNebula, NetApp ONTAP, and NVIDIA technologies combine compute, storage, and orchestration to support AI inference workloads.
• Persistent AI Data with NetApp ONTAP: How centralized model repositories and datasets remain available independently of GPU compute environments, avoiding unnecessary data duplication.
• From Data to Inference: A live demonstration of OpenNebula’s Kubernetes Service (OneKS) provisioning GPU-enabled Kubernetes clusters, NetApp Trident connecting workloads to ONTAP storage, and NVIDIA NIM and Dynamo enabling AI inference services.
• Secure Multi-Tenancy and GPU Management: How OpenNebula provides isolated tenant environments, network policies, and flexible NVIDIA GPU allocation across shared infrastructure.
• On-Demand GPU Environments: How to deploy, scale, and release GPU-powered environments in minutes while preserving access to persistent AI data and improving GPU utilization.
• Live Q&A: Discuss the architecture, integrations, and practical deployment scenarios with our experts.