Tim Trappen | Searcharxiv

arXiv2025

Automated Dynamic AI Inference Scaling on HPC-Infrastructure: Integrating Kubernetes, Slurm and vLLM

Due to rising demands for Artificial Inteligence (AI) inference, especially in higher education, novel solutions utilising existing infrastructure are emerging. The utilisation of High-Performance Computing (HPC) has become a prevalent approach for the implementation of such solutions. However, the classical operating model of HPC does not adapt well to the requirements of synchronous, user-facing dynamic AI application workloads. In this paper, we propose our solution that serves LLMs by integrating vLLM, Slurm and Kubernetes on the supercomputer \textit{RAMSES}. The initial benchmark indicates that the proposed architecture scales efficiently for 100, 500 and 1000 concurrent requests, incurring only an overhead of approximately 500 ms in terms of end-to-end latency.

cs.DC↗

arXiv2025

Campus AI vs Commercial AI: A Late-Breaking Study on How LLM As-A-Service Customizations Shape Trust and Usage Patterns

As the use of Large Language Models (LLMs) by students, lecturers and researchers becomes more prevalent, universities - like other organizations - are pressed to develop coherent AI strategies. LLMs as-a-Service (LLMaaS) offer accessible pre-trained models, customizable to specific (business) needs. While most studies prioritize data, model, or infrastructure adaptations (e.g., model fine-tuning), we focus on user-salient customizations, like interface changes and corporate branding, which we argue influence users' trust and usage patterns. This study serves as a functional prequel to a large-scale field study in which we examine how students and employees at a German university perceive and use their institution's customized LLMaaS compared to ChatGPT. The goals of this prequel are to stimulate discussions on psychological effects of LLMaaS customizations and refine our research approach through feedback. Our forthcoming findings will deepen the understanding of trust dynamics in LLMs, providing practical guidance for organizations considering LLMaaS deployment.

cs.CY↗