{"id":"https://openalex.org/W3165292244","doi":"https://doi.org/10.1145/3437984.3458837","title":"Interference-Aware Scheduling for Inference Serving","display_name":"Interference-Aware Scheduling for Inference Serving","publication_year":2021,"publication_date":"2021-04-25","ids":{"openalex":"https://openalex.org/W3165292244","doi":"https://doi.org/10.1145/3437984.3458837","mag":"3165292244"},"language":"en","primary_location":{"id":"doi:10.1145/3437984.3458837","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437984.3458837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Machine Learning and 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/A5102871320","display_name":"Daniel Mendoza","orcid":"https://orcid.org/0009-0006-3431-6566"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Mendoza","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102022369","display_name":"Francisco Romero","orcid":"https://orcid.org/0000-0001-6902-405X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francisco Romero","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340613","display_name":"Qian Li","orcid":"https://orcid.org/0000-0002-7115-7633"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian Li","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031510918","display_name":"Neeraja J. Yadwadkar","orcid":"https://orcid.org/0009-0007-7556-3069"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neeraja J. Yadwadkar","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042148531","display_name":"Christos Kozyrakis","orcid":"https://orcid.org/0000-0002-3154-7530"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christos Kozyrakis","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"80","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.9958000183105469,"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"}},"topics":[{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.9958000183105469,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.991599977016449,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9876999855041504,"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/computer-science","display_name":"Computer science","score":0.8299801349639893},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8082197904586792},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.8006839156150818},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.7501436471939087},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6813549995422363},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6185559034347534},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5912035703659058},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.43343058228492737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2719714939594269},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.19794711470603943},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14635786414146423},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.10731911659240723},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08254295587539673},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0747135579586029}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8299801349639893},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8082197904586792},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8006839156150818},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7501436471939087},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6813549995422363},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6185559034347534},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5912035703659058},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.43343058228492737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2719714939594269},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.19794711470603943},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14635786414146423},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.10731911659240723},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08254295587539673},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0747135579586029},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3437984.3458837","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437984.3458837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Machine Learning and Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W317957491","https://openalex.org/W1516061453","https://openalex.org/W2015099024","https://openalex.org/W2024247835","https://openalex.org/W2117702591","https://openalex.org/W2266248102","https://openalex.org/W2606722458","https://openalex.org/W2664267452","https://openalex.org/W2887117815","https://openalex.org/W2895934479","https://openalex.org/W2968986602","https://openalex.org/W2999012726","https://openalex.org/W3011434423","https://openalex.org/W3017091196","https://openalex.org/W3043433718","https://openalex.org/W3095488153","https://openalex.org/W4231829227","https://openalex.org/W4236491543"],"related_works":["https://openalex.org/W96612179","https://openalex.org/W2770234245","https://openalex.org/W2566006169","https://openalex.org/W2987774938","https://openalex.org/W632915154","https://openalex.org/W2393741509","https://openalex.org/W3008625068","https://openalex.org/W3128807919","https://openalex.org/W3176411177","https://openalex.org/W3035501883"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"inference":[2,19,75],"applications":[3],"have":[4,65],"proliferated":[5],"through":[6],"diverse":[7],"domains":[8],"such":[9],"as":[10],"healthcare,":[11],"security,":[12],"and":[13,26,53,91],"analytics.":[14],"Recent":[15],"work":[16],"has":[17],"proposed":[18],"serving":[20,76],"systems":[21,77],"for":[22,62],"improving":[23],"the":[24,40,79,87],"deployment":[25],"scalability":[27],"of":[28,81,89],"models.":[29],"To":[30],"improve":[31],"resource":[32],"utilization,":[33],"multiple":[34],"models":[35,90],"can":[36,46,54],"be":[37],"co-located":[38],"on":[39],"same":[41],"backend":[42],"machine.":[43],"However,":[44],"co-location":[45,82],"cause":[47],"latency":[48,57],"degradation":[49],"due":[50],"to":[51,73],"interference":[52],"subsequently":[55],"violate":[56],"requirements.":[58],"Although":[59],"interference-aware":[60],"schedulers":[61],"general":[63],"workloads":[64],"been":[66],"introduced,":[67],"they":[68],"do":[69],"not":[70],"scale":[71],"appropriately":[72],"heterogeneous":[74],"where":[78],"number":[80,88],"configurations":[83],"grows":[84],"exponentially":[85],"with":[86],"machine":[92],"types.":[93]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}