SAIA: a seamless Slurm-native solution for HPC-based services
The Journal of Supercomputing · 08.05.2026 · 82 (7)
DOI: 10.1007/s11227-026-08508-3 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Supercomputing, online erschienen am 08.05.2026. Verfasst von Ali Doosthosseini und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bundesministerium für Bildung und Forschung.
Abstract (Originalsprache)
Recent developments indicate a shift toward web services that employ ever-larger AI models, e.g., large language models (LLMs), requiring powerful and expensive hardware for inference. High-performance computing (HPC) systems are commonly equipped with such hardware for the purpose of large-scale computation tasks. However, HPC infrastructure is inherently unsuitable for hosting real-time web services due to network, security, and scheduling constraints. While various efforts exist to integrate external scheduling solutions, these often require compromises in terms of security or usability for existing HPC users. In this paper, we present SAIA, a Slurm-native platform consisting of a scheduler and a proxy. The scheduler interacts with Slurm to ensure the availability and scalability of services, while the proxy provides external access, which is secured via confined SSH commands. We have demonstrated SAIA’s applicability by deploying a large-scale LLM web service that has served over 100 000 users.
Förderung
- Bundesministerium für Bildung und Forschung
Zitieren
APA
Doosthosseini, A., Decker, J., Nolte, H., & Kunkel, J. (2026). SAIA: a seamless Slurm-native solution for HPC-based services. The Journal of Supercomputing, 82(7). https://doi.org/10.1007/s11227-026-08508-3
Vancouver
Doosthosseini A, Decker J, Nolte H, Kunkel J. SAIA: a seamless Slurm-native solution for HPC-based services. The Journal of Supercomputing. 2026;82(7). doi:10.1007/s11227-026-08508-3
BibTeX
@article{Doosthosseini2026,
author = {Doosthosseini, Ali and Decker, Jonathan and Nolte, Hendrik and Kunkel, Julian},
title = {SAIA: a seamless Slurm-native solution for HPC-based services},
journal = {The Journal of Supercomputing},
year = {2026},
volume = {82},
number = {7},
doi = {10.1007/s11227-026-08508-3}
}
EUVIMED