--- title: "Models in Minutes: A Deep Dive into VMware Private AI Model Runtime" url: https://www.vmware.com/explore/video/6403821341112 description: As organizations race to bring LLMs and AI agents on-premises, the key requirement is deploying models securely and efficiently. In this session, we dive into the VMware Private AI Model Runtime Service, the engine that powers inference at scale across VMware vSphere® and Kubernetes clusters. Learn how its API gateway, load-balancing capabilities, and integrated security streamline model deployment with enterprise-grade governance and performance. This session walks through every aspect of model runtime, from selecting the model, to choosing the inference engine, defining resource requirements (CPU or GPU), to Kubernetes deployment and scaling, to agents communicating with models. --- # Models in Minutes: A Deep Dive into VMware Private AI Model Runtime [Models in Minutes: A Deep Dive into VMware Private AI Model Runtime](https://players.brightcove.net/6164421911001/lUBT2rAMW_default/index.html?videoId=6403821341112) ![Models in Minutes: A Deep Dive into VMware Private AI Model Runtime](https://cf-images.us-east-1.prod.boltdns.net/v1/jit/6164421911001/34d6e0d7-ffe3-411f-a9f6-c46ea2a8cb9f/main/1280x720/22m9s322ms/match/image.jpg) 111 Views ## Abstract As organizations race to bring LLMs and AI agents on-premises, the key requirement is deploying models securely and efficiently. In this session, we dive into the VMware Private AI Model Runtime Service, the engine that powers inference at scale across VMware vSphere® and Kubernetes clusters. Learn how its API gateway, load-balancing capabilities, and integrated security streamline model deployment with enterprise-grade governance and performance. This session walks through every aspect of model runtime, from selecting the model, to choosing the inference engine, defining resource requirements (CPU or GPU), to Kubernetes deployment and scaling, to agents communicating with models. ## Session Info - **Session Code**: INVB1227LV - **Type**: Breakout Session - **Track**: Innovation - **Products**: VMware Cloud Foundation Private AI Services - **Level**: Technical 300 - **Event Delivery**: [Las Vegas](https://www.vmware.com/explore/us) - **Year**: 2026 ## Speakers ### Shawn Kelly Sr. Principal Architect, AI Broadcom ![Shawn Kelly](https://static.rainfocus.com/vmware/explore2026lv/att/1714159170573001xSiE/attprofile/Shawn_1785860406412001xZu2.jpeg) Shawn is a Sr. Principal Architect in San Diego, California focused on delivering innovative AI/ML solutions. Shawn holds Master of Science degrees in Software Engineering and IT Management from the Naval Postgraduate School in 2010. In the decade preceding he served as a Marine Helicopter Pilot. ### Frank Denneman Distinguished Engineer Broadcom ![Frank Denneman](https://static.rainfocus.com/vmware/explore2026lv/att/1714411836431001jigA/attprofile/headshot_1786699905295001Sngc.jpg) Frank Denneman is the Chief Technologist AI for VMware by Broadcom. Frank focussed on AI technology. He is an author of the vSphere host and clustering deep dive series. Frank can be followed on LinkedIn. ## Presentation PDF [Download](https://static.rainfocus.com/vmware/explore2026lv/sess/1776185439515001xQlQ/presrevpdf/INVB1227LV_1788456886435001hk9h.pdf) ## Related Videos ### [Introducing VMware AI Factory: The Software-Defined Foundation of VMware Private AI Cloud](https://www.vmware.com/explore/video/6403821753112) ![Introducing VMware AI Factory: The Software-Defined Foundation of VMware Private AI Cloud](https://cf-images.us-east-1.prod.boltdns.net/v1/jit/6164421911001/79fe2d0a-b81e-4d1f-8610-03f20c869af6/main/1280x720/21m44s576ms/match/image.jpg) CLOB1244LV | 341 views This session will provide an overview of VMware AI Factory, which offers customers a simplified path to production AI with new automation innovations for deploying AI-ready infrastructure and supporting Day 2 operations. Join us and learn how VMware AI Factory brings AI applications directly to enterprise private data within a secure VMware Cloud Foundation (VCF) private cloud environment and reduces the time from bare metal server deployment to serving the first AI model from weeks to a matter of hours. ### [Deploy and govern AI models and agents with VMware Cloud Foundation Private AI Services](https://www.vmware.com/explore/video/6403821751112) ![Deploy and govern AI models and agents with VMware Cloud Foundation Private AI Services](https://cf-images.us-east-1.prod.boltdns.net/v1/jit/6164421911001/c4cf886b-09dd-4f9c-bc2f-dc8fbc3e4b38/main/1280x720/24m21s984ms/match/image.jpg) CLOB1229LV | 61 views Is your organization ready to move beyond the Shadow AI phase into a governed, production-ready state? Managing the fragmented lifecycle of large language models (LLMs), vector databases, and autonomous agents can result in operational silos. This session details integrating a GitOps framework with VMware Cloud Foundation® (VCF) Private AI Services to solve these complexities by automating model management, incorporating data sources, and deploying models and agents through version-controlled manifests. Discover how these manifests further enhance the lifecycle of AI applications. By treating AI components as code, you can accelerate delivery, ensure data sovereignty, and eliminate manual configuration drift. Join us for a technical deep dive into building a declarative, resilient AI infrastructure on VCF. ### [From Frontier Models to Private AI Agents: The Tanzu Harness on VMware Cloud Foundation](https://www.vmware.com/explore/video/6403821925112) ![From Frontier Models to Private AI Agents: The Tanzu Harness on VMware Cloud Foundation](https://cf-images.us-east-1.prod.boltdns.net/v1/jit/6164421911001/e7380dab-7fb1-448a-b5fe-c1ca6c7c8d67/main/1280x720/22m39s403ms/match/image.jpg) INVB1058LV | 41 views When your agent runs on someone else’s cloud, you are not just outsourcing compute—you are outsourcing judgment. That control lives in the harness—how an agent retrieves data, reasons, and acts. Today, that harness is increasingly delivered as a managed service by the frontier AI labs. In regulated environments, that is a non-starter. This session presents a blueprint for running a full agentic stack inside your boundary on VMware Cloud Foundation® (VCF). We will show how to deploy private AI agents using VMware Cloud Foundation® Private AI Services, VMware Tanzu® Platform, VMware Tanzu® Data Intelligence, Symantec®, Layer7 API Gateway, and Automic® Automation. Through a live multi-domain scenario, you will see agents operate in an air-gapped environment—fusing signals and producing explainable outcomes. You will leave with a concrete architecture for deploying regulated AI agents.