Build your own AI datacenter

A hands-on experience Picking up where the last session left off, this talk moves from planning to doing. Ehsan walks through bringing up a home AI server step by step: installing and configuring the OS, getting GPU drivers and the CUDA stack working, setting up a runtime like Ollama or vLLM, and pulling down and serving your first local model. Along the way he covers the details that usually trip people up, including containerization, exposing the server on your home network, and keeping things running after a reboot. This is a hands-on session, so bring your machine and follow along. By the end, you'll have a clear, repeatable path from bare box to a working model endpoint you can hit from any device in the house. Speaker: Ehsan J — https://www.linkedin.com/in/ehsanj/