{"paper":{"title":"Chat AI: A Seamless Slurm-Native Solution for HPC-Based Services","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Ali Doosthosseini, Hendrik Nolte, Jonathan Decker, Julian M. Kunkel","submitted_at":"2024-06-27T12:08:21Z","abstract_excerpt":"The widespread adoption of large language models (LLMs) has created a pressing need for an efficient, secure and private serving infrastructure, which allows researchers to run open source or custom fine-tuned LLMs and ensures users that their data remains private and is not stored without their consent. While high-performance computing (HPC) systems equipped with state-of-the-art GPUs are well-suited for training LLMs, their batch scheduling paradigm is not designed to support real-time serving of AI applications. Cloud systems, on the other hand, are well suited for web services but commonly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00110","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.00110/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}