{"id":"https://openalex.org/W7108903566","doi":"https://doi.org/10.1145/3769836","title":"TranSQL <sup>+</sup> : Serving Large Language Models with SQL on Low-Resource Hardware","display_name":"TranSQL <sup>+</sup> : Serving Large Language Models with SQL on Low-Resource Hardware","publication_year":2025,"publication_date":"2025-12-04","ids":{"openalex":"https://openalex.org/W7108903566","doi":"https://doi.org/10.1145/3769836"},"language":"en","primary_location":{"id":"doi:10.1145/3769836","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769836","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3769836","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wenbo Sun","orcid":"https://orcid.org/0009-0004-7849-7771"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Wenbo Sun","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"raw_orcid":"https://orcid.org/0009-0004-7849-7771","affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiming Guo","orcid":"https://orcid.org/0009-0002-5545-8361"},"institutions":[{"id":"https://openalex.org/I96749437","display_name":"Texas A&M University \u2013 Corpus Christi","ror":"https://ror.org/01mrfdz82","country_code":"US","type":"education","lineage":["https://openalex.org/I96749437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiming Guo","raw_affiliation_strings":["Texas A&amp;M University - Corpus Christi, Corpus Christi, USA"],"raw_orcid":"https://orcid.org/0009-0002-5545-8361","affiliations":[{"raw_affiliation_string":"Texas A&amp;M University - Corpus Christi, Corpus Christi, USA","institution_ids":["https://openalex.org/I96749437"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenlu Wang","orcid":"https://orcid.org/0000-0002-4829-1068"},"institutions":[{"id":"https://openalex.org/I96749437","display_name":"Texas A&M University \u2013 Corpus Christi","ror":"https://ror.org/01mrfdz82","country_code":"US","type":"education","lineage":["https://openalex.org/I96749437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenlu Wang","raw_affiliation_strings":["Texas A&amp;M University - Corpus Christi, Corpus Christi, USA"],"raw_orcid":"https://orcid.org/0000-0002-4829-1068","affiliations":[{"raw_affiliation_string":"Texas A&amp;M University - Corpus Christi, Corpus Christi, USA","institution_ids":["https://openalex.org/I96749437"]}]},{"author_position":"last","author":{"id":null,"display_name":"Rihan Hai","orcid":"https://orcid.org/0000-0002-3720-6585"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Rihan Hai","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-3720-6585","affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75990668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"6","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.4578999876976013,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.4578999876976013,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T14347","display_name":"Big Data and Digital Economy","score":0.09690000116825104,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.050599999725818634,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/sql","display_name":"SQL","score":0.6603000164031982},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5932999849319458},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.44830000400543213},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.448199987411499},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.44440001249313354},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42239999771118164},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.42010000348091125},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.35249999165534973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8705999851226807},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6603000164031982},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6082000136375427},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5932999849319458},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.44440001249313354},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42239999771118164},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.35249999165534973},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33880001306533813},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3368000090122223},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C40207289","wikidata":"https://www.wikidata.org/wiki/Q755662","display_name":"Relational model","level":3,"score":0.31220000982284546},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769836","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769836","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3769836","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769836","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1537358968","display_name":null,"funder_award_id":"2112631","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2103670492","https://openalex.org/W2563724055","https://openalex.org/W2889897289","https://openalex.org/W2948405945","https://openalex.org/W2949054050","https://openalex.org/W3030051638","https://openalex.org/W3081168214","https://openalex.org/W3083309655","https://openalex.org/W3122286897","https://openalex.org/W3194839481","https://openalex.org/W4288365054","https://openalex.org/W4387321091","https://openalex.org/W4389518760","https://openalex.org/W4399534541","https://openalex.org/W4399554253","https://openalex.org/W4401660192","https://openalex.org/W4402670146","https://openalex.org/W4402671659","https://openalex.org/W4402671950","https://openalex.org/W4403245104","https://openalex.org/W4404181190","https://openalex.org/W4404781870","https://openalex.org/W4409348182","https://openalex.org/W4416111774"],"related_works":[],"abstract_inverted_index":{"Deploying":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"on":[5,51,84,125],"resource-constrained":[6],"devices":[7],"remains":[8],"challenging":[9],"due":[10],"to":[11,93,104],"limited":[12],"memory,":[13],"lack":[14],"of":[15,20],"GPUs,":[16],"and":[17,64,86,98,107,111],"the":[18],"complexity":[19],"existing":[21],"runtimes.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26],"introduce":[27],"TranSQL":[28,54,89],"+":[29,55,90],",":[30,56],"a":[31,72,120],"template-based":[32],"code":[33],"generator":[34],"that":[35,76],"translates":[36],"LLM":[37],"computation":[38],"graphs":[39],"into":[40],"pure":[41],"SQL":[42],"queries":[43],"for":[44,123],"execution":[45,63],"in":[46,80,109],"relational":[47,117],"databases.":[48],"Without":[49],"relying":[50],"external":[52],"libraries,":[53],"leverages":[57],"mature":[58],"database":[59],"features-such":[60],"as":[61,119],"vectorized":[62],"out-of-core":[65],"processing-for":[66],"efficient":[67],"inference.":[68],"We":[69],"further":[70],"propose":[71],"row-to-column":[73],"(ROW2COL)":[74],"optimization":[75],"improves":[77],"join":[78],"efficiency":[79],"matrix":[81],"operations.":[82],"Evaluated":[83],"Llama3-8B":[85],"DeepSeekMoE":[87],"models,":[88],"achieves":[91],"up":[92],"20\u00d7":[94],"lower":[95],"prefill":[96],"latency":[97],"4\u00d7":[99],"higher":[100],"decoding":[101],"speed":[102],"compared":[103],"DeepSpeed":[105],"Inference":[106],"Llama.cpp":[108],"low-memory":[110],"CPU-only":[112],"configurations.":[113],"Our":[114],"results":[115],"highlight":[116],"databases":[118],"practical":[121],"environment":[122],"LLMs":[124],"low-resource":[126],"hardware.":[127]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-12-06T00:00:00"}