{"id":"https://openalex.org/W7170095339","doi":"https://doi.org/10.1145/3785462.3815802","title":"Service-Oriented Architecture for an On-Premises AI Gateway Without an On-Premises Cloud","display_name":"Service-Oriented Architecture for an On-Premises AI Gateway Without an On-Premises Cloud","publication_year":2026,"publication_date":"2026-07-22","ids":{"openalex":"https://openalex.org/W7170095339","doi":"https://doi.org/10.1145/3785462.3815802"},"language":null,"primary_location":{"id":"doi:10.1145/3785462.3815802","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785462.3815802","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3785462.3815802","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085571988","display_name":"Ronald Rahaman","orcid":"https://orcid.org/0000-0002-8917-8934"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ronald Rahaman","raw_affiliation_strings":["Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8917-8934","affiliations":[{"raw_affiliation_string":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453054","display_name":"Fang Liu","orcid":"https://orcid.org/0000-0002-3383-2191"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fang Liu","raw_affiliation_strings":["Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3383-2191","affiliations":[{"raw_affiliation_string":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102985047","display_name":"Pratik Shah","orcid":"https://orcid.org/0000-0003-4017-7583"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pratik Shah","raw_affiliation_strings":["Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0009-0002-0764-1233","affiliations":[{"raw_affiliation_string":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039438503","display_name":"Kenneth J. Suda","orcid":"https://orcid.org/0000-0002-2770-0192"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenneth Suda","raw_affiliation_strings":["Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2770-0192","affiliations":[{"raw_affiliation_string":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040371111","display_name":"Matthew Guidry","orcid":"https://orcid.org/0000-0003-4432-5029"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matt Guidry","raw_affiliation_strings":["Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4432-5029","affiliations":[{"raw_affiliation_string":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038703321","display_name":"Michael D. Weiner","orcid":"https://orcid.org/0000-0002-7601-0702"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael D. Weiner","raw_affiliation_strings":["Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7601-0702","affiliations":[{"raw_affiliation_string":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074170797","display_name":"Jeffrey Young","orcid":"https://orcid.org/0000-0001-9841-4057"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Young","raw_affiliation_strings":["Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9841-4057","affiliations":[{"raw_affiliation_string":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093236228","display_name":"Allan Metts","orcid":"https://orcid.org/0000-0001-5432-1676"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allan Metts","raw_affiliation_strings":["Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5432-1676","affiliations":[{"raw_affiliation_string":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7667999863624573},{"id":"https://openalex.org/keywords/gateway","display_name":"Gateway (web page)","score":0.6420000195503235},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.6378999948501587},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6309000253677368},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5422999858856201},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.47429999709129333},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.46889999508857727},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.462799996137619}],"concepts":[{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7667999863624573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7635999917984009},{"id":"https://openalex.org/C2777710495","wikidata":"https://www.wikidata.org/wiki/Q5527195","display_name":"Gateway (web page)","level":2,"score":0.6420000195503235},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.6378999948501587},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6309000253677368},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5422999858856201},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.462799996137619},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.40700000524520874},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3889000117778778},{"id":"https://openalex.org/C35869016","wikidata":"https://www.wikidata.org/wiki/Q846636","display_name":"Software architecture","level":3,"score":0.3158999979496002},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.313400000333786},{"id":"https://openalex.org/C57041688","wikidata":"https://www.wikidata.org/wiki/Q220644","display_name":"Service-oriented architecture","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3050000071525574},{"id":"https://openalex.org/C53619493","wikidata":"https://www.wikidata.org/wiki/Q4787093","display_name":"Architecture framework","level":3,"score":0.30309998989105225},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.3003999888896942},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C120115606","wikidata":"https://www.wikidata.org/wiki/Q5135723","display_name":"Cloud testing","level":4,"score":0.28349998593330383},{"id":"https://openalex.org/C179703994","wikidata":"https://www.wikidata.org/wiki/Q1755130","display_name":"Residential gateway","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C187713609","wikidata":"https://www.wikidata.org/wiki/Q2465461","display_name":"Default gateway","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3785462.3815802","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785462.3815802","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3785462.3815802","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785462.3815802","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W4284970215","https://openalex.org/W4386585104","https://openalex.org/W4387321091","https://openalex.org/W4413059345","https://openalex.org/W7128390792"],"related_works":[],"abstract_inverted_index":{"We":[0,95,125,142],"describe":[1],"the":[2,81,92,97],"architecture,":[3],"implementation,":[4],"and":[5,42,61,68,89,99,111,130,137],"initial":[6],"deployment":[7],"of":[8,51,58,85],"a":[9,49],"scalable,":[10],"fully":[11],"on-premises":[12,21],"AI":[13,54],"Gateway":[14,55],"that":[15,144],"does":[16],"not":[17],"rely":[18],"on":[19],"existing":[20],"cloud":[22],"infrastructure.":[23],"Our":[24,53],"service-oriented":[25],"architecture":[26],"is":[27,56],"well-suited":[28],"for":[29,152],"publicly-funded":[30],"High":[31],"Performance":[32],"Computing":[33],"sites":[34,154],"who":[35],"manage":[36,43],"GPU":[37],"hardware":[38],"via":[39,91,103,123],"batch":[40],"scheduling":[41],"CPU":[44],"virtual":[45],"machine":[46],"(VM)s":[47],"through":[48,119],"variety":[50],"means.":[52],"composed":[57],"industry-proven":[59],"free":[60],"open-source":[62],"software":[63],"services":[64,101,116],"(including":[65],"LiteLLM,":[66],"vLLM,":[67],"Triton":[69],"Inference":[70],"Server).":[71],"As":[72],"an":[73],"API-first":[74],"service,":[75],"it":[76],"provides":[77],"excellent":[78],"interoperability":[79],"with":[80,105,155],"established":[82],"third-party":[83],"ecosystem":[84],"LLM":[86,114],"clients":[87],"applications":[88],"libraries":[90],"OpenAI":[93],"API.":[94],"deploy":[96],"proxy":[98],"accounting":[100],"(LiteLLM)":[102],"Podman":[104],"systemd":[106],"integration":[107],"provided":[108],"by":[109],"Quadlet,":[110],"we":[112],"provide":[113,149],"inference":[115],"(vLLM,":[117],"Triton)":[118],"continuously-scheduled":[120],"Slurm":[121],"jobs":[122],"scrontab.":[124],"present":[126],"preliminary":[127,132],"load":[128],"testing":[129],"summarize":[131],"use":[133],"cases":[134],"among":[135],"researchers":[136],"students":[138],"at":[139],"our":[140,145],"site.":[141],"hope":[143],"architectural":[146],"description":[147],"will":[148],"sufficient":[150],"details":[151],"other":[153],"similar":[156,160],"constraints":[157],"to":[158],"implement":[159],"services.":[161]},"counts_by_year":[],"updated_date":"2026-07-23T06:02:39.697066","created_date":"2026-07-23T00:00:00"}
