AI-Events

You are looking for events  relevant to working with artificial intelligence methods on high-performance computers?
Here we offer you the filtered calendar of the Gaussian Alliance (all organizers, not only NHR!):
(Calendar source: GA HPC calendar)

AI - From Laptop to Supercomputer
Next date Thursday 16.04.26 at 2-4 pm

Eventlink: go-nhr.de/ai_on_hpc_vconf | Language: English
Contact: aionsupercomputer@nhr-verein.de

AI - Open Q&A Hour
Every Thursday at 2-4 pm (not  on April 16)

Eventlink: go-nhr.de/ai_on_hpc_vconf | Language: English
Contact: aionsupercomputer@nhr-verein.de

AI - Open Q&A Hour with a special focus

Last Open Q&A Hour with a special focus: 12.02.26

Eventlink: go-nhr.de/ai_on_hpc_vconf | Language: English
Contact: aionsupercomputer@nhr-verein.de

Mini Tutorial
Automated Dynamic AI Inference Scaling on HPC-Infrastructure: Integrating Kubernetes, Slurm and vLLM 
To tackle the rising demand for (generative) AI inference, especially in higher education, utilising already existing computing infrastructure like High-Performance Computing (HPC) seems to be a straightforward solution. However, the classical operating model of HPC is usually not tailored to the requirements of synchronous, user-facing applications. To tackle this, we propose a solution that fully integrates the cloud-native Kubernetes with HPC-native Slurm to deploy vLLM, a Large Language Model (LLM) inference-engine for high-throughput scenarios. Our solution allows for automatically scaling the number of deployed models based on actual hardware load, while leveraging the job scheduling mechanisms provided by Slurm to efficiently maximise load on inference hardware, thus freeing unneeded hardware for scientific computing jobs. In addition, we provide initial performance benchmarks for two typical HPC compute-node hardware configurations and an outlook on aspects we want to improve in the near future. As our solution is already running in a production scenario for an ever-increasing number of higher education institutions across North Rhine-Westphalia, we are open to discuss our experiences with this operating model following the presentation.

You can find more information about our AI services here.