GOOD 2026

Large language models are now a common tool for writing code and exploring ideas, but using them on HPC systems can still be a challenge. To make this simpler, I built an interactive Open OnDemand application that lets users access a local LLM directly inside Jupyter Notebook using the Jupyter AI extension. Behind the scenes, user requests are routed through a load balancer to a pool of vLLM inference servers running on Intel GPUs, which serve open-source models up to 70B parameters.

In this talk, I’ll walk through how the system works, why we built it, and how it gives researchers easy, reliable access to LLM assistance without relying on external cloud services.

Machine learning now plays a very important role in a wide range of scientific fields. However many researchers in these scientific fields don't have machine learning expertise and may find it difficult to train a machine learning model themselves.
Auto machine learning bridges this gap by making it very simple to train a state of the art model. Auto machine learning frameworks like AutoGluon make it such that all you need is a dataset and a few lines of code.
The interactive application that I have developed for Open OnDemand closes the gap further by not requiring the user to write any code at all. Through our application, users can simply choose a dataset and their configuration, and train the model.