{"id":"https://openalex.org/W4408894550","doi":"https://doi.org/10.1145/3676641.3716261","title":"K <scp>lotski</scp> : Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline","display_name":"K <scp>lotski</scp> : Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline","publication_year":2025,"publication_date":"2025-03-27","ids":{"openalex":"https://openalex.org/W4408894550","doi":"https://doi.org/10.1145/3676641.3716261"},"language":"en","primary_location":{"id":"doi:10.1145/3676641.3716261","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676641.3716261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","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/A5103636056","display_name":"Zhiyuan Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyuan Fang","raw_affiliation_strings":["Sun Yat-sen University, Zhuhai, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113216608","display_name":"Yisheng Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuegui Huang","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075795671","display_name":"Zicong Hong","orcid":"https://orcid.org/0000-0001-5689-382X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zicong Hong","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017305346","display_name":"Yufeng Lyu","orcid":"https://orcid.org/0000-0002-6531-8277"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufeng Lyu","raw_affiliation_strings":["Huawei Technologies Co. Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066482792","display_name":"Wuhui Chen","orcid":"https://orcid.org/0000-0003-4430-7904"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wuhui Chen","raw_affiliation_strings":["Sun Yat-sen University, Zhuhai, China and Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Zhuhai, China and Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397991","display_name":"Yue Yu","orcid":"https://orcid.org/0000-0002-9865-2212"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Yu","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101814062","display_name":"Yu Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yu","raw_affiliation_strings":["Huawei Technologies Co. Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000582109","display_name":"Zibin Zheng","orcid":"https://orcid.org/0000-0002-7878-4330"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zibin Zheng","raw_affiliation_strings":["Sun Yat-sen University, Zhuhai, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5103636056"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":2.4849,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88812921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"574","last_page":"588"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9973000288009644,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9973000288009644,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9835000038146973,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.982699990272522,"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/pipeline","display_name":"Pipeline (software)","score":0.7522091865539551},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6906799077987671},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6811458468437195},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.45628082752227783},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3193354606628418},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2006680965423584}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7522091865539551},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6906799077987671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6811458468437195},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.45628082752227783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3193354606628418},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2006680965423584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3676641.3716261","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676641.3716261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","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":16,"referenced_works":["https://openalex.org/W2734941459","https://openalex.org/W2979826702","https://openalex.org/W2990138404","https://openalex.org/W3012479151","https://openalex.org/W3012514909","https://openalex.org/W3119866685","https://openalex.org/W3205803342","https://openalex.org/W4213153339","https://openalex.org/W4220967350","https://openalex.org/W4287391717","https://openalex.org/W4318541554","https://openalex.org/W4321636575","https://openalex.org/W4382319938","https://openalex.org/W4396827044","https://openalex.org/W4401211627","https://openalex.org/W6605862995"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2389542812","https://openalex.org/W2390279801","https://openalex.org/W2381894592","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2030629278"],"abstract_inverted_index":{"Mixture":[0],"of":[1,12,18],"Experts":[2],"(MoE),":[3],"with":[4,44],"its":[5],"distinctive":[6],"sparse":[7],"structure,":[8],"enables":[9],"the":[10,26,36,45,55,61,67,79,86],"scaling":[11],"language":[13],"models":[14,74],"up":[15],"to":[16],"trillions":[17],"parameters":[19],"without":[20],"significantly":[21],"increasing":[22],"computational":[23],"costs.":[24],"However,":[25],"substantial":[27],"parameter":[28],"size":[29],"presents":[30],"a":[31],"challenge":[32],"for":[33,65,69],"inference,":[34],"as":[35],"expansion":[37],"in":[38,47,72,82,85],"GPU":[39],"memory":[40,53],"cannot":[41],"keep":[42],"pace":[43],"growth":[46],"parameters.":[48],"Although":[49],"offloading":[50],"techniques":[51],"utilise":[52],"from":[54],"CPU":[56],"and":[57,59,63],"disk":[58],"parallelise":[60],"I/O":[62],"computation":[64,68],"efficiency,":[66],"each":[70],"expert":[71],"MoE":[73],"is":[75],"often":[76],"less":[77],"than":[78],"I/O,":[80],"resulting":[81],"numerous":[83],"bubbles":[84],"pipeline.":[87]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}