{"id":"https://openalex.org/W7155538430","doi":"https://doi.org/10.1145/3767295.3769319","title":"Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading","display_name":"Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W7155538430","doi":"https://doi.org/10.1145/3767295.3769319"},"language":null,"primary_location":{"id":"doi:10.1145/3767295.3769319","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769319","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 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767295.3769319","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075787386","display_name":"Hanfei Yu","orcid":"https://orcid.org/0000-0001-5790-4981"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanfei Yu","raw_affiliation_strings":["Stevens Institute of Technology, Hoboken, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0001-5790-4981","affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology, Hoboken, NJ, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049563917","display_name":"Xingqi Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xingqi Cui","raw_affiliation_strings":["Rice University, Houston, Texas, USA"],"raw_orcid":"https://orcid.org/0009-0003-9561-0118","affiliations":[{"raw_affiliation_string":"Rice University, Houston, Texas, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016938862","display_name":"Hong Zhang","orcid":"https://orcid.org/0000-0001-7468-3746"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hong Zhang","raw_affiliation_strings":["University of Waterloo, Waterloo, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0001-7468-3746","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006209345","display_name":"H Y Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Rutgers University, New Brunswick, NJ, USA","Stevens Institue of Technology, Hoboken, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-7308-938X","affiliations":[{"raw_affiliation_string":"Rutgers University, New Brunswick, NJ, USA","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Stevens Institue of Technology, Hoboken, NJ, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006209345","display_name":"H Y Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Rutgers University, New Brunswick, NJ, USA","Stevens Institue of Technology, Hoboken, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-1444-2657","affiliations":[{"raw_affiliation_string":"Rutgers University, New Brunswick, NJ, USA","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Stevens Institue of Technology, Hoboken, NJ, USA","institution_ids":["https://openalex.org/I108468826"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.57555874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"176","last_page":"191"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.11140000075101852,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.11140000075101852,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.1096000000834465,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.09510000050067902,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/troubleshooting","display_name":"Troubleshooting","score":0.350600004196167},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.30630001425743103},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.301800012588501},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.30070000886917114},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.29510000348091125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4738999903202057},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2883000075817108},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3767295.3769319","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769319","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 21st European Conference on Computer Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3767295.3769319","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769319","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 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G140527694","display_name":null,"funder_award_id":"2527416","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2448029082","display_name":null,"funder_award_id":"R01CA297832","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4002626585","display_name":null,"funder_award_id":"2127918","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6697622589","display_name":null,"funder_award_id":"2340125","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7226432234","display_name":null,"funder_award_id":"2523997","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7234062446","display_name":null,"funder_award_id":"2534241","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"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W317957491","https://openalex.org/W4402671950"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"gained":[5],"immense":[6],"success":[7],"in":[8],"revolutionizing":[9],"various":[10],"applications,":[11],"including":[12],"content":[13],"generation,":[14],"search":[15],"and":[16,18],"recommendation,":[17],"AI-assisted":[19],"operations.":[20],"To":[21],"reduce":[22],"high":[23,78,82],"training":[24],"costs,":[25],"Mixture-of-Experts":[26],"(MoE)":[27],"architecture":[28],"has":[29],"become":[30],"a":[31],"popular":[32],"backbone":[33],"for":[34],"modern":[35],"LLMs.":[36],"However,":[37,74],"despite":[38],"the":[39,68],"benefits,":[40],"serving":[41,69],"MoE-based":[42],"LLMs":[43],"experience":[44],"severe":[45],"memory":[46,62,65,84],"inefficiency":[47],"due":[48,86],"to":[49,56,63,66,87],"sparsely":[50],"activated":[51],"experts.":[52],"Recent":[53],"studies":[54],"propose":[55],"offload":[57],"inactive":[58],"experts":[59],"from":[60],"GPU":[61],"CPU":[64],"improve":[67],"efficiency":[70],"of":[71],"MoE":[72],"models.":[73],"they":[75],"either":[76],"incur":[77],"inference":[79],"latency":[80],"or":[81],"model":[83],"footprints":[85],"coarse-grained":[88],"designs.":[89]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-25T00:00:00"}