{"id":"https://openalex.org/W2944614352","doi":"https://doi.org/10.1145/3317550.3321443","title":"A Case for Managed and Model-less Inference Serving","display_name":"A Case for Managed and Model-less Inference Serving","publication_year":2019,"publication_date":"2019-05-10","ids":{"openalex":"https://openalex.org/W2944614352","doi":"https://doi.org/10.1145/3317550.3321443","mag":"2944614352"},"language":"en","primary_location":{"id":"doi:10.1145/3317550.3321443","doi":"https://doi.org/10.1145/3317550.3321443","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3317550.3321443","pdf_url":null,"source":{"id":"https://openalex.org/S4306421247","display_name":"Workshop on Hot Topics in Operating Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Hot Topics in Operating Systems","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5031510918","display_name":"Neeraja J. Yadwadkar","orcid":"https://orcid.org/0009-0007-7556-3069","observed_orcids":["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":"middle","author":{"id":"https://openalex.org/A5102022369","display_name":"Francisco Romero","orcid":"https://orcid.org/0000-0001-6902-405X","observed_orcids":["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","observed_orcids":["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":"last","author":{"id":"https://openalex.org/A5042148531","display_name":"Christos Kozyrakis","orcid":"https://orcid.org/0000-0002-3154-7530","observed_orcids":["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, Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Google","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":3.197,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.93306582,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"184","last_page":"191"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9286999702453613,"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":0.9286999702453613,"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":0.011300000362098217,"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/T12127","display_name":"Software System Performance and Reliability","score":0.010599999688565731,"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-serving","display_name":"inference serving","score":0.9070000052452087},{"id":"https://openalex.org/keywords/machine-learning-inference","display_name":"machine learning inference","score":0.7379999756813049},{"id":"https://openalex.org/keywords/neural-network","display_name":"artificial neural networks","score":0.8379999995231628},{"id":"https://openalex.org/keywords/model-selection","display_name":"model selection","score":0.7300000190734863},{"id":"https://openalex.org/keywords/model-optimization","display_name":"model optimization","score":0.9039999842643738},{"id":"https://openalex.org/keywords/horizontal-scaling","display_name":"horizontal scaling","score":0.722000002861023},{"id":"https://openalex.org/keywords/cost-constraints","display_name":"cost constraints","score":0.43299999833106995},{"id":"https://openalex.org/keywords/dynamic-resource-allocation","display_name":"dynamic resource allocation","score":0.5820000171661377}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8515588045120239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8478130102157593},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5983699560165405},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5269951224327087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5056214332580566},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.464399129152298},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3317550.3321443","doi":"https://doi.org/10.1145/3317550.3321443","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3317550.3321443","pdf_url":null,"source":{"id":"https://openalex.org/S4306421247","display_name":"Workshop on Hot Topics in Operating Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Hot Topics in Operating Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2075233755","https://openalex.org/W2138243089","https://openalex.org/W2198403777","https://openalex.org/W2412412865","https://openalex.org/W2419597278","https://openalex.org/W2568772110","https://openalex.org/W2591324491","https://openalex.org/W2605258629","https://openalex.org/W2606722458","https://openalex.org/W2626699878","https://openalex.org/W2734593428","https://openalex.org/W2767421475","https://openalex.org/W2772948367","https://openalex.org/W2794670651","https://openalex.org/W2798353737","https://openalex.org/W2807462012","https://openalex.org/W2883929540","https://openalex.org/W2886050937","https://openalex.org/W2886464150","https://openalex.org/W2887117815","https://openalex.org/W2887712657","https://openalex.org/W2887901326","https://openalex.org/W2888975141","https://openalex.org/W2895511477","https://openalex.org/W2897070804","https://openalex.org/W2901394833","https://openalex.org/W2906773779","https://openalex.org/W2962741697","https://openalex.org/W2962746093","https://openalex.org/W2962786581","https://openalex.org/W2963674932","https://openalex.org/W2964108773","https://openalex.org/W4253695895","https://openalex.org/W4394670654"],"related_works":["https://openalex.org/W2947883979","https://openalex.org/W2976643737","https://openalex.org/W3111036603","https://openalex.org/W3119908787","https://openalex.org/W3080306393","https://openalex.org/W4399911840","https://openalex.org/W7154641557","https://openalex.org/W3039010666","https://openalex.org/W4391799240","https://openalex.org/W4368353274"],"abstract_inverted_index":{"The":[0],"number":[1],"of":[2,28,63],"applications":[3,25,65,112],"relying":[4],"on":[5],"inference":[6,29,42],"from":[7],"machine":[8],"learning":[9],"models,":[10],"especially":[11,104],"neural":[12],"networks,":[13],"is":[14],"already":[15],"large":[16,68],"and":[17,37,60,80,93,116],"expected":[18],"to":[19,48,66,102],"keep":[20],"growing.":[21],"For":[22],"instance,":[23],"Facebook":[24],"issue":[26],"tens-of-trillions":[27],"queries":[30],"per":[31],"day":[32],"with":[33],"varying":[34],"performance,":[35,58],"accuracy,":[36,59],"cost":[38,51,61],"constraints.":[39],"Unfortunately,":[40],"today's":[41],"serving":[43],"systems":[44],"are":[45,100],"neither":[46],"easy":[47],"use":[49],"nor":[50],"effective.":[52],"Developers":[53],"must":[54],"manually":[55],"match":[56],"the":[57,77,84,89,106,117],"constraints":[62],"their":[64],"a":[67],"design":[69],"space":[70],"that":[71],"includes":[72],"decisions":[73,99],"such":[74],"as":[75],"selecting":[76,83,88],"right":[78,85,90],"model":[79,81],"optimizations,":[82],"hardware":[86],"architecture,":[87],"scale-out":[91],"factor,":[92],"avoiding":[94],"cold-start":[95],"effects.":[96],"These":[97],"interacting":[98],"difficult":[101],"make,":[103],"when":[105],"application":[107],"load":[108],"varies":[109],"over":[110,114,121],"time,":[111,115],"evolve":[113],"available":[118],"resources":[119],"vary":[120],"time.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-05-16T00:00:00"}