{"id":"https://openalex.org/W7123842037","doi":"https://doi.org/10.1145/3772052.3772207","title":"Multiplexed Heterogeneous LLM Serving via Stage-Aligned Parallelism","display_name":"Multiplexed Heterogeneous LLM Serving via Stage-Aligned Parallelism","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W7123842037","doi":"https://doi.org/10.1145/3772052.3772207"},"language":null,"primary_location":{"id":"doi:10.1145/3772052.3772207","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772052.3772207","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 2025 ACM Symposium on Cloud Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3772052.3772207","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103054884","display_name":"Tao Luo","orcid":"https://orcid.org/0009-0003-4406-1841"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tao Luo","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, Pennsylvania, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109069665","display_name":"Kelvin K.W. Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kelvin K.W. Ng","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, Pennsylvania, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122957975","display_name":"Zhen Ping Khor","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhen Ping Khor","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, Pennsylvania, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047803229","display_name":"Sidharth Sankhe","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sidharth Sankhe","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, Pennsylvania, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090052860","display_name":"Boon Thau Loo","orcid":"https://orcid.org/0000-0002-4757-1746"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boon Thau Loo","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, Pennsylvania, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122972887","display_name":"Vincent Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vincent Liu","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, Pennsylvania, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103054884"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71619366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"735","last_page":"747"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.3686999976634979,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.3686999976634979,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.10809999704360962,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.06599999964237213,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/control-reconfiguration","display_name":"Control reconfiguration","score":0.645799994468689},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5393000245094299},{"id":"https://openalex.org/keywords/multiplexing","display_name":"Multiplexing","score":0.44200000166893005},{"id":"https://openalex.org/keywords/portfolio","display_name":"Portfolio","score":0.3725999891757965},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.29789999127388},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.29089999198913574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080999851226807},{"id":"https://openalex.org/C119701452","wikidata":"https://www.wikidata.org/wiki/Q5165881","display_name":"Control reconfiguration","level":2,"score":0.645799994468689},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5953999757766724},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5393000245094299},{"id":"https://openalex.org/C19275194","wikidata":"https://www.wikidata.org/wiki/Q222903","display_name":"Multiplexing","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35659998655319214},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32030001282691956},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3772052.3772207","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772052.3772207","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 2025 ACM Symposium on Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3772052.3772207","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772052.3772207","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 2025 ACM Symposium on Cloud Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W3206832494","https://openalex.org/W4387321091","https://openalex.org/W4401211704","https://openalex.org/W4409248734"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"LLM":[1],"serving":[2],"workloads":[3],"are":[4],"increasingly":[5],"heterogeneous,":[6],"involving":[7],"a":[8],"growing":[9],"portfolio":[10],"of":[11],"models":[12],"with":[13],"vastly":[14],"different":[15],"compute":[16],"and":[17,32],"memory":[18],"requirements.":[19],"Existing":[20],"approaches":[21],"to":[22,29,35],"model":[23],"serving-ranging":[24],"from":[25],"static":[26],"GPU":[27,33],"partitioning":[28],"dynamic":[30],"reconfiguration":[31],"multiplexing\u2014fail":[34],"effectively":[36],"support":[37],"heterogeneity.":[38]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-01-14T00:00:00"}
