{"id":"https://openalex.org/W4415256993","doi":"https://doi.org/10.1145/3767295.3769316","title":"FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters","display_name":"FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W4415256993","doi":"https://doi.org/10.1145/3767295.3769316"},"language":"en","primary_location":{"id":"doi:10.1145/3767295.3769316","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769316","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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767295.3769316","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033311175","display_name":"Yanying Lin","orcid":"https://orcid.org/0000-0002-4809-9543"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yanying Lin","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences, Shenzhen, Guangdong, China","UC San Diego, San Diego, California, USA","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4809-9543","affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"UC San Diego, San Diego, California, USA","institution_ids":["https://openalex.org/I2800935791"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102014822","display_name":"Shijie Peng","orcid":"https://orcid.org/0009-0005-1776-4773"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijie Peng","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences, Shenzhen, Guangdong, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-1776-4773","affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103176699","display_name":"Chengzhi Lu","orcid":"https://orcid.org/0000-0002-6421-3828"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Chengzhi Lu","raw_affiliation_strings":["University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0000-0002-6421-3828","affiliations":[{"raw_affiliation_string":"University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012773300","display_name":"Chengzhong Xu","orcid":"https://orcid.org/0000-0001-9480-0356"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"ChengZhong Xu","raw_affiliation_strings":["University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0000-0001-9480-0356","affiliations":[{"raw_affiliation_string":"University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012757772","display_name":"Kejiang Ye","orcid":"https://orcid.org/0000-0001-6133-407X"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejiang Ye","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-6133-407X","affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":47.0898,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.99393204,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"72","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9868999719619751,"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":0.9868999719619751,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9847000241279602,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9735000133514404,"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/code-refactoring","display_name":"Code refactoring","score":0.7946000099182129},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6477000117301941},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6014999747276306},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5792999863624573},{"id":"https://openalex.org/keywords/reservation","display_name":"Reservation","score":0.5616999864578247},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.45890000462532043},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4571000039577484}],"concepts":[{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.7946000099182129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904000282287598},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6477000117301941},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6014999747276306},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.593999981880188},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5792999863624573},{"id":"https://openalex.org/C2777632111","wikidata":"https://www.wikidata.org/wiki/Q1937518","display_name":"Reservation","level":2,"score":0.5616999864578247},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.45890000462532043},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4341999888420105},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35499998927116394},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3160000145435333},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C109751979","wikidata":"https://www.wikidata.org/wiki/Q998767","display_name":"Failover","level":2,"score":0.2700999975204468}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3767295.3769316","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769316","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"},{"id":"pmh:oai:arXiv.org:2510.11938","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.11938","pdf_url":"https://arxiv.org/pdf/2510.11938","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3767295.3769316","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769316","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/G5840464552","display_name":null,"funder_award_id":"2023B1515130002","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G6248574994","display_name":null,"funder_award_id":"2021TQ06X990","funder_id":"https://openalex.org/F4320336642","funder_display_name":"Guangdong Special Support Plan"},{"id":"https://openalex.org/G7672641152","display_name":null,"funder_award_id":"92267105","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336642","display_name":"Guangdong Special Support Plan","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Serving":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"in":[5,19],"production":[6],"faces":[7],"significant":[8],"challenges":[9],"from":[10],"highly":[11],"variable":[12],"request":[13],"patterns":[14],"and":[15],"severe":[16],"resource":[17],"fragmentation":[18],"serverless":[20],"clusters.":[21],"Current":[22],"systems":[23],"rely":[24],"on":[25],"static":[26],"pipeline":[27],"configurations":[28],"that":[29],"struggle":[30],"to":[31,33,38],"adapt":[32],"dynamic":[34],"workload":[35],"conditions,":[36],"leading":[37],"substantial":[39],"inefficiencies.":[40]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-17T00:00:00"}
