{"id":"https://openalex.org/W4366341968","doi":"https://doi.org/10.1145/3579371.3589038","title":"OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization","display_name":"OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization","publication_year":2023,"publication_date":"2023-06-16","ids":{"openalex":"https://openalex.org/W4366341968","doi":"https://doi.org/10.1145/3579371.3589038"},"language":"en","primary_location":{"id":"doi:10.1145/3579371.3589038","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579371.3589038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.07493","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101706991","display_name":"Cong Guo","orcid":"https://orcid.org/0000-0002-4479-5525"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cong Guo","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Shanghai Qi Zhi Institute, Shanghai, China","Shanghai Jiao Tong University, Shanghai, China Shanghai Qi Zhi Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210122302"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103244882","display_name":"Jiaming Tang","orcid":"https://orcid.org/0009-0004-4186-6561"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Tang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Shanghai Qi Zhi Institute, Shanghai, China","Shanghai Jiao Tong University, Shanghai, China Shanghai Qi Zhi Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210122302"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101721549","display_name":"Weiming Hu","orcid":"https://orcid.org/0009-0003-5115-0498"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Hu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Shanghai Qi Zhi Institute, Shanghai, China","Shanghai Jiao Tong University, Shanghai, China Shanghai Qi Zhi Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210122302"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003939279","display_name":"Jingwen Leng","orcid":"https://orcid.org/0000-0002-5660-5493"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwen Leng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Shanghai Qi Zhi Institute, Shanghai, China","Shanghai Jiao Tong University, Shanghai, China Shanghai Qi Zhi Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210122302"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374175","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0003-2762-2726"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346602","display_name":"Fan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102880548","display_name":"Yunxin Liu","orcid":"https://orcid.org/0000-0001-7352-8955"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunxin Liu","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China","Shanghai Artificial Intelligence Laboratory, Shanghai, China","Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minyi Guo","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Shanghai Qi Zhi Institute, Shanghai, China","Shanghai Jiao Tong University, Shanghai, China Shanghai Qi Zhi Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210122302"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023684582","display_name":"Yuhao Zhu","orcid":"https://orcid.org/0000-0002-2802-0578"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhao Zhu","raw_affiliation_strings":["University of Rochester, Rochester, New York, USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, New York, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101706991"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210122302"],"apc_list":null,"apc_paid":null,"fwci":21.7456,"has_fulltext":true,"cited_by_count":125,"citation_normalized_percentile":{"value":0.99636488,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9961000084877014,"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/computer-science","display_name":"Computer science","score":0.6657193899154663},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.597240686416626},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5170422196388245},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3320358097553253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2704593241214752},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2514804005622864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6657193899154663},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.597240686416626},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5170422196388245},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3320358097553253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2704593241214752},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2514804005622864}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3579371.3589038","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579371.3589038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2304.07493","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.07493","pdf_url":"https://arxiv.org/pdf/2304.07493","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.07493","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.07493","pdf_url":"https://arxiv.org/pdf/2304.07493","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2465329715","display_name":null,"funder_award_id":"61832006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3841266055","display_name":null,"funder_award_id":"6222221","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3940808221","display_name":null,"funder_award_id":"62222210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8826274250","display_name":null,"funder_award_id":"62072297","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366341968.pdf","grobid_xml":"https://content.openalex.org/works/W4366341968.grobid-xml"},"referenced_works_count":89,"referenced_works":["https://openalex.org/W1606129576","https://openalex.org/W1841592590","https://openalex.org/W1979527452","https://openalex.org/W2000967104","https://openalex.org/W2023214828","https://openalex.org/W2044535169","https://openalex.org/W2048266589","https://openalex.org/W2067523571","https://openalex.org/W2094756095","https://openalex.org/W2117696986","https://openalex.org/W2150139096","https://openalex.org/W2156077332","https://openalex.org/W2194775991","https://openalex.org/W2242818861","https://openalex.org/W2323909431","https://openalex.org/W2442974303","https://openalex.org/W2464177207","https://openalex.org/W2469490737","https://openalex.org/W2516141709","https://openalex.org/W2604514113","https://openalex.org/W2606722458","https://openalex.org/W2786771851","https://openalex.org/W2804032941","https://openalex.org/W2883920103","https://openalex.org/W2884150179","https://openalex.org/W2896457183","https://openalex.org/W2904902077","https://openalex.org/W2923014074","https://openalex.org/W2963122961","https://openalex.org/W2963148663","https://openalex.org/W2963367920","https://openalex.org/W2963480671","https://openalex.org/W2963748441","https://openalex.org/W2963989532","https://openalex.org/W2970601456","https://openalex.org/W2980186997","https://openalex.org/W2981758446","https://openalex.org/W2982041622","https://openalex.org/W2982479999","https://openalex.org/W2998183051","https://openalex.org/W3005664618","https://openalex.org/W3012249773","https://openalex.org/W3016542674","https://openalex.org/W3018278400","https://openalex.org/W3024621361","https://openalex.org/W3034887213","https://openalex.org/W3034940165","https://openalex.org/W3034999214","https://openalex.org/W3043504674","https://openalex.org/W3092209569","https://openalex.org/W3092319711","https://openalex.org/W3100985894","https://openalex.org/W3102510044","https://openalex.org/W3115555382","https://openalex.org/W3132616766","https://openalex.org/W3133253223","https://openalex.org/W3158444059","https://openalex.org/W3165976180","https://openalex.org/W3177265267","https://openalex.org/W3187908937","https://openalex.org/W3190062760","https://openalex.org/W3213241618","https://openalex.org/W4213153339","https://openalex.org/W4214512541","https://openalex.org/W4221162983","https://openalex.org/W4226109952","https://openalex.org/W4229005866","https://openalex.org/W4234212765","https://openalex.org/W4234833047","https://openalex.org/W4240168186","https://openalex.org/W4242577057","https://openalex.org/W4251575795","https://openalex.org/W4253012315","https://openalex.org/W4280546523","https://openalex.org/W4287118909","https://openalex.org/W4288026258","https://openalex.org/W4292119927","https://openalex.org/W4293327315","https://openalex.org/W4295312788","https://openalex.org/W4297813615","https://openalex.org/W4297948009","https://openalex.org/W4298392854","https://openalex.org/W4308083739","https://openalex.org/W4311642023","https://openalex.org/W4312060054","https://openalex.org/W4312513797","https://openalex.org/W4318541535","https://openalex.org/W4385245566","https://openalex.org/W6662587704"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W3006513224","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2046456988","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Transformer-based":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"have":[5],"achieved":[6],"great":[7],"success":[8],"with":[9,56],"the":[10,24,41,51,82,105],"growing":[11],"model":[12,29],"size.":[13],"LLMs'":[14],"size":[15,46],"grows":[16],"by":[17],"240\u00d7":[18],"every":[19],"two":[20],"years,":[21],"which":[22],"outpaces":[23],"hardware":[25,48,97],"progress":[26],"and":[27,47,99,109,118],"makes":[28,61],"inference":[30],"increasingly":[31],"costly.":[32],"Model":[33],"quantization":[34,63,69,123],"is":[35,115],"a":[36,88],"promising":[37],"approach":[38],"to":[39,75],"mitigate":[40],"widening":[42],"gap":[43],"between":[44,107],"LLM":[45],"capacity.":[49],"However,":[50],"existence":[52],"of":[53],"outliers,":[54],"values":[55,80],"significant":[57],"magnitudes,":[58],"in":[59],"LLMs":[60],"existing":[62],"methods":[64],"less":[65],"effective.":[66],"Prior":[67],"outlier-aware":[68],"schemes":[70],"adopt":[71],"sparsity":[72,90],"encoding":[73],"techniques":[74],"separate":[76],"outliers":[77],"from":[78],"normal":[79,110],"where":[81],"process":[83],"requires":[84],"global":[85,89],"coordination":[86,91],"(e.g.,":[87],"list).":[92],"This":[93],"incurs":[94],"complex":[95],"encoding/decoding":[96],"logics":[98],"an":[100],"extra":[101],"orchestration":[102],"controller":[103],"for":[104],"computation":[106],"outlier":[108],"values.":[111],"As":[112],"such,":[113],"it":[114],"not":[116],"hardware-efficient":[117],"hence":[119],"only":[120],"achieves":[121],"sub-optimal":[122],"benefits.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":70},{"year":2024,"cited_by_count":41},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}