{"id":"https://openalex.org/W4414898304","doi":"https://doi.org/10.1109/escience65000.2025.00059","title":"AI Model Serving on HPC Infrastructure","display_name":"AI Model Serving on HPC Infrastructure","publication_year":2025,"publication_date":"2025-09-15","ids":{"openalex":"https://openalex.org/W4414898304","doi":"https://doi.org/10.1109/escience65000.2025.00059"},"language":"en","primary_location":{"id":"doi:10.1109/escience65000.2025.00059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience65000.2025.00059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on eScience (eScience)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084488102","display_name":"Rohan Marwaha","orcid":"https://orcid.org/0009-0007-1488-5398"},"institutions":[{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rohan Marwaha","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,National Center for Supercomputing Applications,Urbana,IL,USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,National Center for Supercomputing Applications,Urbana,IL,USA","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080618069","display_name":"Qi Zhou","orcid":"https://orcid.org/0000-0002-5818-061X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qinren Zhou","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,Department of Electrical and Computer Engineering,Urbana,IL,USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,Department of Electrical and Computer Engineering,Urbana,IL,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102841844","display_name":"Kastan Day","orcid":"https://orcid.org/0000-0002-1989-3406"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kastan Day","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,National Center for Supercomputing Applications,Urbana,IL,USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,National Center for Supercomputing Applications,Urbana,IL,USA","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060025664","display_name":"Volodymyr Kindratenko","orcid":"https://orcid.org/0000-0002-9336-4756"},"institutions":[{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Volodymyr Kindratenko","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,National Center for Supercomputing Applications,Urbana,IL,USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,National Center for Supercomputing Applications,Urbana,IL,USA","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084488102"],"corresponding_institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34460031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"337","last_page":"338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.7738999724388123,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.7738999724388123,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.6668999791145325,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6342999935150146},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6061000227928162},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.454800009727478},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4490000009536743},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.39559999108314514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7791000008583069},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6342999935150146},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6061000227928162},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4196999967098236},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3490000069141388},{"id":"https://openalex.org/C2778383056","wikidata":"https://www.wikidata.org/wiki/Q873636","display_name":"Namespace","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32710000872612},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.30410000681877136},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.26019999384880066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/escience65000.2025.00059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience65000.2025.00059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on eScience (eScience)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4401861917"],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"two":[2],"open-source":[3],"frameworks":[4,69],"for":[5,30,76],"deploying":[6],"and":[7,83],"running":[8],"large":[9],"language":[10],"models":[11],"(LLMs)":[12],"within":[13],"the":[14,50],"constraints":[15],"of":[16,34,62],"high-performance":[17],"computing":[18],"(HPC)":[19],"clusters":[20],"managed":[21],"by":[22],"SLURM":[23],"job":[24],"scheduler.":[25],"One":[26],"framework":[27,52],"is":[28],"designed":[29],"high-throughput":[31],"batch":[32],"inference":[33,78],"LLM":[35],"requests":[36],"using":[37],"an":[38],"OpenAI-compatible":[39],"format,":[40],"enabling":[41],"users":[42,85],"to":[43,58,72,86],"submit":[44],"traditional":[45],"HPC-style":[46],"workloads.":[47],"Complementing":[48],"this,":[49],"other":[51],"allows":[53],"dynamically":[54],"allocating":[55],"HPC":[56,74],"resources":[57,75],"provide":[59],"interactive":[60],"serving":[61],"LLMs":[63],"accessible":[64],"via":[65],"API":[66],"calls.":[67],"Both":[68],"enable":[70],"researchers":[71],"request":[73],"model":[77],"on-demand,":[79],"eliminating":[80],"setup":[81],"complexities":[82],"allowing":[84],"focus":[87],"exclusively":[88],"on":[89],"their":[90],"core":[91],"research.":[92]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
