Search for: All records

The Rosen Center for Advanced Computing at Purdue University has recently released two Generative AI inference tools, AnvilGPT and Purdue GenAI Studio, to the research and campus communities. These services support over 1000 users who use 10+ open-source GenAI models to aid their work. Building on HPC’s long history of using open-source tools, these services are based on customized open-source frameworks and hosted entirely on-prem. This pa- per argues that building custom GenAI services from open-source frameworks is a scalable and cost-effective solution for providing access to Generative AI models. This paper shares the methodology and resources required to develop and host these services and seeks to be a resource for other research computing centers that wish to leverage their HPC investment to create similar services. 

Accurate wait-time prediction for HPC jobs contributes to a positive user experience but has historically been a challenging task. Previous models lack the accuracy needed for confident predictions, and many were developed before the rise of deep learning. In this work, we investigate and develop TROUT, a neural network-based model to accurately predict wait times for jobs submitted to the Anvil HPC cluster. Data was taken from the Slurm Workload Manager on the cluster and transformed before performing additional feature engineering from jobs’ priorities, partitions, and states. We developed a hierarchical model that classifies job queue times into bins before applying regression, outperforming traditional methods. The model was then integrated into a CLI tool for queue time prediction. This study explores which queue time prediction methods are most applicable for modern HPC systems and shows that deep learning-based prediction models are viable solutions. 

This paper reports on the lessons learned from developing and deploying campus-wide large language model (LLM) services at Purdue University for generative AI (GenAI) applications in education and research. We present a frame- work for identifying an LLM solution suite and identify key considerations related to developing custom solutions. While the GenAI ecosystem continues to evolve, the framework is intended to provide a tool- and organization-agnostic approach to guide leaders in conversations and strategy for future work and collaboration in this emerging field.