Turning Supercomputers into AI Platforms: Live Demo of HelixML + Interlink on a European HPC

Watch a live technical demo of deploying modern AI infrastructure on HPC systems. See how HelixML and Interlink work together to run LLMs like Llama3 on the Vega supercomputer in Slovenia, complete with multi-tenant isolation, automated testing, and API integrations. Perfect for HPC admins, ML engineers, and anyone interested in running private AI infrastructure.

In this demo:

Deploy ChatGPT-like capabilities on Slurm clusters
Run open source LLMs on supercomputer GPUs
Add multi-tenant security to HPC infrastructure
Build and test AI applications with version control
Integrate external APIs with LLM applications

Featuring Luke Marsden (HelixML) and Diego Ciangottini from INFN demonstrating how to bridge the gap between traditional HPC and modern AI infrastructure.

---
Diego Ciangottini is a physicist and received his PhD from the University of Perugia, Italy in 2012. Now he’s working as technologist at INFN (Italian National Institute for Nuclear Physics) researching cloud-native solutions for the scientific use cases of the institute. In that sense his main occupation is building bridges between science communities and what the cloud-native ecosystem can do for them.

Thank you to Diego and the InterTwin project – it has been a true pleasure to work with you! Check out what they are doing here: https://www.intertwin.eu/

#AI #HPC #Supercomputing #MachineLearning #TechDemo