In today’s world, where businesses have fully embraced the power of chatbots and Large Language Models (LLMs), many forget the risk of feeding public AI services with sensitive data. Organizations that do see the risk and choose to run LLMs in their own datacenter experience challenges because MLops teams have trouble to scale their infrastructure. This is where the newly announced VMware Private AI Foundation, that includes VMware vSphere with Tanzu and NVIDIA AI Enterprise, can help. In this session, Johan van Amersfoort (ITQ), Frank Denneman (VMware), and Jits Langedijk (NVIDIA) will explain how organizations can implement ML apps like chatbots with LLMs in their own environment, using the same modern tools and DevOps processes as admins would do when running them in public cloud. They will explain aspects like hardware configs and show you how easy it is to deploy your own LLM using NVIDIA GPU Cloud!