{"id":"https://openalex.org/W4415124561","doi":"https://doi.org/10.1109/icmlt65785.2025.11193187","title":"S4T-GPTQ: A Space-for-Time Strategy For Optimizing GPTQ 4-bit Quantization","display_name":"S4T-GPTQ: A Space-for-Time Strategy For Optimizing GPTQ 4-bit Quantization","publication_year":2025,"publication_date":"2025-05-23","ids":{"openalex":"https://openalex.org/W4415124561","doi":"https://doi.org/10.1109/icmlt65785.2025.11193187"},"language":"en","primary_location":{"id":"doi:10.1109/icmlt65785.2025.11193187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlt65785.2025.11193187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Machine Learning Technologies (ICMLT)","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/A5052915634","display_name":"Yaozheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaozheng Zhang","raw_affiliation_strings":["Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101416524","display_name":"Mengxiao Wang","orcid":"https://orcid.org/0000-0003-4904-463X"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxiao Wang","raw_affiliation_strings":["Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083123801","display_name":"Yuhao Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Peng","raw_affiliation_strings":["Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331851","display_name":"Yunpeng Liu","orcid":"https://orcid.org/0000-0002-7942-2112"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunpeng Liu","raw_affiliation_strings":["Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072694505","display_name":"Jiehan Zhou","orcid":"https://orcid.org/0000-0002-4026-1649"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiehan Zhou","raw_affiliation_strings":["Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100510275","display_name":"Haojie Zhou","orcid":"https://orcid.org/0000-0002-2536-2222"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haojie Zhou","raw_affiliation_strings":["JiangNan University,School of Aritificial Intelligence and Computer Science,Wuxi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JiangNan University,School of Aritificial Intelligence and Computer Science,Wuxi,China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004582171","display_name":"Shouhua Zhang","orcid":"https://orcid.org/0000-0002-8225-1350"},"institutions":[{"id":"https://openalex.org/I63586086","display_name":"Oulu University of Applied Sciences","ror":"https://ror.org/03dvp8k55","country_code":"FI","type":"education","lineage":["https://openalex.org/I63586086"]},{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Shouhua Zhang","raw_affiliation_strings":["University of Oulu,Faculty of Information Technology and Computer Science,Oulu,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oulu,Faculty of Information Technology and Computer Science,Oulu,Finland","institution_ids":["https://openalex.org/I98381234","https://openalex.org/I63586086"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000202379","display_name":"Huanqing Cui","orcid":"https://orcid.org/0000-0002-9251-680X"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanqing Cui","raw_affiliation_strings":["Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24922994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"383","last_page":"387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.899399995803833,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.899399995803833,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.8108000159263611,"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/T11269","display_name":"Algorithms and Data Compression","score":0.8076000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6669999957084656},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6133999824523926},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4855000078678131},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4320000112056732},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42080000042915344},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.3440999984741211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8029000163078308},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6669999957084656},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6133999824523926},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4855000078678131},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41819998621940613},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3601999878883362},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.3440999984741211},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25999999046325684},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlt65785.2025.11193187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlt65785.2025.11193187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Machine Learning Technologies (ICMLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2088134616","https://openalex.org/W2798317693","https://openalex.org/W3127943551","https://openalex.org/W4387321091","https://openalex.org/W4391136507","https://openalex.org/W4392427708","https://openalex.org/W4392454577","https://openalex.org/W4393152626","https://openalex.org/W4402473798","https://openalex.org/W4402474001","https://openalex.org/W4402727033","https://openalex.org/W4402753294","https://openalex.org/W4404918643","https://openalex.org/W4405305316","https://openalex.org/W4405362385"],"related_works":[],"abstract_inverted_index":{"Frequent":[0],"global":[1,50],"memory":[2,39,51],"accesses":[3],"and":[4,62,81],"computational":[5],"complexity":[6],"often":[7],"become":[8],"significant":[9],"performance":[10],"bottlenecks":[11],"in":[12,90],"large":[13,86],"language":[14,87],"model":[15],"(LLM)":[16],"inference.":[17],"To":[18],"address":[19],"this":[20,22],"challenge,":[21],"paper":[23],"proposes":[24],"a":[25],"space-for-time":[26],"strategy":[27],"for":[28,84],"opti-mizing":[29],"GPTQ":[30,69],"4-bit":[31,70],"quantization,":[32],"namely":[33],"S4T-GPTQ.":[34],"The":[35],"S4T-GPTQ":[36,57],"leverages":[37],"shared":[38],"blocks":[40],"to":[41],"store":[42],"intermediate":[43],"results,":[44],"significantly":[45],"reducing":[46],"the":[47,59,64,68,73],"number":[48],"of":[49,67],"accesses.":[52],"Experimental":[53],"results":[54],"show":[55],"that":[56],"improves":[58],"inference":[60,65],"throughput":[61],"reduces":[63],"latency":[66],"quantization":[71],"under":[72],"vLLM":[74],"framework.":[75],"These":[76],"enhancements":[77],"provide":[78],"an":[79],"efficient":[80],"practical":[82],"solution":[83],"deploying":[85],"models":[88],"(LLMs)":[89],"high-throughput,":[91],"low-latency":[92],"scenarios.":[93]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-14T00:00:00"}
