{"id":"https://openalex.org/W4394945037","doi":"https://doi.org/10.1145/3642970.3655844","title":"ALTO","display_name":"ALTO","publication_year":2024,"publication_date":"2024-04-19","ids":{"openalex":"https://openalex.org/W4394945037","doi":"https://doi.org/10.1145/3642970.3655844"},"language":"en","primary_location":{"id":"doi:10.1145/3642970.3655844","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3642970.3655844","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 4th Workshop on Machine Learning and Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3642970.3655844","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026521456","display_name":"Keshav Santhanam","orcid":"https://orcid.org/0000-0001-5939-7944"},"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":true,"raw_author_name":"Keshav Santhanam","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050070176","display_name":"Deepti Raghavan","orcid":"https://orcid.org/0000-0003-2341-1155"},"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":"Deepti Raghavan","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011298605","display_name":"Muhammad Shahir Rahman","orcid":"https://orcid.org/0009-0006-5723-9997"},"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":"Muhammad Shahir Rahman","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038940016","display_name":"Thejas Venkatesh","orcid":"https://orcid.org/0000-0002-9561-6101"},"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":"Thejas Venkatesh","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094105660","display_name":"Neha Kunjal","orcid":null},"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":"Neha Kunjal","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011471473","display_name":"Pratiksha Thaker","orcid":"https://orcid.org/0000-0001-9977-5081"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pratiksha Thaker","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060306684","display_name":"Philip Levis","orcid":"https://orcid.org/0000-0003-2934-2701"},"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":"Philip Levis","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005554337","display_name":"Matei Zaharia","orcid":"https://orcid.org/0000-0002-7547-7204"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matei Zaharia","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5026521456"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.4669,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83902793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9947999715805054,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/stateful-firewall","display_name":"Stateful firewall","score":0.8546373248100281},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8431563377380371},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.646168053150177},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6212519407272339},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4762818217277527},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.44760861992836},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4296836256980896},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4291527271270752},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2374488115310669},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1848311424255371},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.09077754616737366}],"concepts":[{"id":"https://openalex.org/C22927095","wikidata":"https://www.wikidata.org/wiki/Q1784206","display_name":"Stateful firewall","level":3,"score":0.8546373248100281},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431563377380371},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.646168053150177},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6212519407272339},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4762818217277527},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44760861992836},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4296836256980896},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4291527271270752},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2374488115310669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1848311424255371},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.09077754616737366},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3642970.3655844","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3642970.3655844","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 4th Workshop on Machine Learning and Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3642970.3655844","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3642970.3655844","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 4th Workshop on Machine Learning and Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1976821017","https://openalex.org/W2010801412","https://openalex.org/W2062735494","https://openalex.org/W2082171780","https://openalex.org/W2126022651","https://openalex.org/W2798434712","https://openalex.org/W2981937105","https://openalex.org/W3095488153","https://openalex.org/W3176171201","https://openalex.org/W3217305727","https://openalex.org/W4306317212","https://openalex.org/W4387321091","https://openalex.org/W4389520047","https://openalex.org/W4393160302"],"related_works":["https://openalex.org/W2583381754","https://openalex.org/W2144255176","https://openalex.org/W2222333653","https://openalex.org/W109977192","https://openalex.org/W1970797462","https://openalex.org/W2566747981","https://openalex.org/W4312120139","https://openalex.org/W2809541058","https://openalex.org/W2342453732","https://openalex.org/W2167609832"],"abstract_inverted_index":{"We":[0,40],"present":[1],"ALTO,":[2],"a":[3,101,118,123],"network":[4],"orchestrator":[5],"for":[6,81,100],"efficiently":[7],"serving":[8,47,120],"compound":[9],"AI":[10],"systems":[11],"such":[12],"as":[13],"pipelines":[14],"of":[15,71,105],"language":[16,26,35,65],"models.":[17],"ALTO":[18],"leverages":[19],"an":[20,82],"optimization":[21],"opportunity":[22],"specific":[23],"to":[24,37,98,117],"generative":[25],"models,":[27],"which":[28],"is":[29],"streaming":[30,93],"intermediate":[31],"outputs":[32],"from":[33],"the":[34,79],"model":[36],"downstream":[38],"stages.":[39],"highlight":[41],"two":[42],"challenges":[43],"that":[44],"emerge":[45],"while":[46],"these":[48,75],"applications":[49],"at":[50],"scale:":[51],"handling":[52,63],"how":[53,64],"some":[54],"stages":[55],"can":[56,67],"be":[57],"stateful":[58],"across":[59],"partial":[60,91],"outputs,":[61],"and":[62,86,110],"models":[66],"produce":[68],"variable":[69],"amounts":[70],"text.":[72],"To":[73],"address":[74],"challenges,":[76],"we":[77],"motivate":[78],"need":[80],"aggregation-aware":[83],"routing":[84],"interface":[85],"distributed":[87],"prompt-aware":[88],"scheduling.":[89],"ALTO's":[90],"output":[92],"increases":[94],"throughput":[95],"by":[96,114],"up":[97],"3\u00d7":[99],"fixed":[102],"latency":[103,113],"target":[104],"4":[106],"seconds":[107],"/":[108],"request":[109],"reduces":[111],"tail":[112],"1.8\u00d7":[115],"compared":[116],"baseline":[119],"approach,":[121],"on":[122],"complex":[124],"chat":[125],"bot":[126],"verification":[127],"pipeline.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2024-04-19T00:00:00"}