{"id":"https://openalex.org/W4394923129","doi":"https://doi.org/10.1145/3627703.3629567","title":"Optimus: Warming Serverless ML Inference via Inter-Function Model Transformation","display_name":"Optimus: Warming Serverless ML Inference via Inter-Function Model Transformation","publication_year":2024,"publication_date":"2024-04-18","ids":{"openalex":"https://openalex.org/W4394923129","doi":"https://doi.org/10.1145/3627703.3629567"},"language":"en","primary_location":{"id":"doi:10.1145/3627703.3629567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627703.3629567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth European Conference on Computer Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5075795671","display_name":"Zicong Hong","orcid":"https://orcid.org/0000-0001-5689-382X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zicong Hong","raw_affiliation_strings":["Hong Kong Polytechnic University"],"raw_orcid":"https://orcid.org/0000-0001-5689-382X","affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018887232","display_name":"Lin Jian","orcid":"https://orcid.org/0000-0001-9130-7320"},"institutions":[{"id":"https://openalex.org/I32574673","display_name":"Shantou University","ror":"https://ror.org/01a099706","country_code":"CN","type":"education","lineage":["https://openalex.org/I32574673"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Lin","raw_affiliation_strings":["Shantou University"],"raw_orcid":"https://orcid.org/0000-0001-9130-7320","affiliations":[{"raw_affiliation_string":"Shantou University","institution_ids":["https://openalex.org/I32574673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043464306","display_name":"Song Guo","orcid":"https://orcid.org/0000-0001-9831-2202"},"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":"Song Guo","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":"https://orcid.org/0000-0001-9831-2202","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072586902","display_name":"S Y Luo","orcid":"https://orcid.org/0009-0003-1473-1795"},"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":"Sifu Luo","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":"https://orcid.org/0009-0003-1473-1795","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"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 and Peng Cheng Laboratory"],"raw_orcid":"https://orcid.org/0000-0003-4430-7904","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University and Peng Cheng Laboratory","institution_ids":["https://openalex.org/I157773358","https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078339613","display_name":"Roger Wattenhofer","orcid":"https://orcid.org/0000-0002-6339-3134"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Roger Wattenhofer","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":"https://orcid.org/0000-0002-6339-3134","affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","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"],"raw_orcid":"https://orcid.org/0000-0002-9865-2212","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1039","last_page":"1053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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":0.998199999332428,"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"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9979000091552734,"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/inference","display_name":"Inference","score":0.8321876525878906},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7992609143257141},{"id":"https://openalex.org/keywords/container","display_name":"Container (type theory)","score":0.6493087410926819},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6357914805412292},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.62333744764328},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5506613850593567},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5486796498298645},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5386597514152527},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4710778295993805},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37314116954803467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23217341303825378},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2089621126651764},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.15727078914642334},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14463496208190918},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10320955514907837}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8321876525878906},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7992609143257141},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.6493087410926819},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6357914805412292},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.62333744764328},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5506613850593567},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5486796498298645},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5386597514152527},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4710778295993805},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37314116954803467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23217341303825378},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2089621126651764},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.15727078914642334},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14463496208190918},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10320955514907837},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3627703.3629567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627703.3629567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth European Conference on Computer Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-131638","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-131638","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2734941459","https://openalex.org/W2911351991","https://openalex.org/W2963761135","https://openalex.org/W2996705685","https://openalex.org/W2997561286","https://openalex.org/W3012028616","https://openalex.org/W3029471531","https://openalex.org/W3031868945","https://openalex.org/W3101868768","https://openalex.org/W3130689885","https://openalex.org/W3155705005","https://openalex.org/W3169257120","https://openalex.org/W4205761438","https://openalex.org/W4213019189","https://openalex.org/W4214610523","https://openalex.org/W4214690606","https://openalex.org/W4282576498","https://openalex.org/W4294904165","https://openalex.org/W4321636606","https://openalex.org/W4372260324","https://openalex.org/W4372263930","https://openalex.org/W4386245182"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W2931688134","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W3128807919","https://openalex.org/W3176411177"],"abstract_inverted_index":{"Serverless":[0],"ML":[1,16,70,123],"inference":[2,12,34,71,174],"is":[3,20,56,84],"an":[4,98,152],"emerging":[5],"cloud":[6],"computing":[7],"paradigm":[8],"for":[9,121,143,159],"low-cost,":[10],"easy-to-manage":[11],"services.":[13],"In":[14],"serverless":[15,69,122],"inference,":[17,124],"each":[18],"call":[19],"executed":[21],"in":[22,32,105,180],"a":[23,67,76,89,102,106,114,132,138,160],"container;":[24],"however,":[25],"the":[26,57,86],"cold":[27],"start":[28],"of":[29,88,117,135,140,168],"containers":[30,52,130],"results":[31],"long":[33],"delays.":[35],"Unfortunately,":[36],"most":[37],"existing":[38,99],"works":[39],"do":[40],"not":[41],"work":[42],"well":[43],"because":[44],"they":[45],"still":[46],"need":[47],"to":[48,187],"load":[49],"models":[50,128,169],"into":[51,127],"from":[53],"scratch,":[54],"which":[55,125],"bottleneck":[58],"based":[59],"on":[60,166],"our":[61],"observations.":[62],"Therefore,":[63],"this":[64],"paper":[65],"proposes":[66],"low-latency":[68],"system":[72],"called":[73],"Optimus":[74,172],"via":[75],"new":[77,90],"container":[78],"management":[79],"scheme.":[80],"Our":[81,164],"key":[82],"insight":[83],"that":[85,171],"loading":[87],"model":[91,100,119,148],"can":[92],"be":[93],"significantly":[94],"accelerated":[95],"when":[96],"using":[97],"with":[101,156],"similar":[103],"structure":[104],"warm":[107],"but":[108],"idle":[109],"container.":[110],"We":[111],"thus":[112],"develop":[113],"novel":[115],"idea":[116],"inter-function":[118],"transformation":[120,162],"delves":[126],"within":[129],"at":[131],"finer":[133],"granularity":[134],"operations,":[136],"designs":[137],"set":[139],"in-container":[141],"meta-operators":[142],"both":[144,181],"CNN":[145],"and":[146,150,183],"transformer":[147],"transformation,":[149],"develops":[151],"efficient":[153],"scheduling":[154],"algorithm":[155],"linear":[157],"complexity":[158],"low-cost":[161],"strategy.":[163],"evaluations":[165],"thousands":[167],"show":[170],"reduces":[173],"latency":[175],"by":[176],"24.00%":[177],"~":[178],"47.56%":[179],"simulated":[182],"real-world":[184],"workloads":[185],"compared":[186],"state-of-the-art":[188],"work.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
