{"id":"https://openalex.org/W4413921941","doi":"https://doi.org/10.1145/3748273.3749196","title":"RTT- or Bandwidth-Bound? Demystifying the KV Cache Transfer in Large Language Model Serving","display_name":"RTT- or Bandwidth-Bound? Demystifying the KV Cache Transfer in Large Language Model Serving","publication_year":2025,"publication_date":"2025-09-02","ids":{"openalex":"https://openalex.org/W4413921941","doi":"https://doi.org/10.1145/3748273.3749196"},"language":"en","primary_location":{"id":"doi:10.1145/3748273.3749196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3748273.3749196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Networks for AI Computing","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/A5053173593","display_name":"Shengnan Yue","orcid":"https://orcid.org/0000-0003-1002-4789"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengnan Yue","raw_affiliation_strings":["China Mobile Research Institute, China Mobile"],"raw_orcid":"https://orcid.org/0000-0003-1002-4789","affiliations":[{"raw_affiliation_string":"China Mobile Research Institute, China Mobile","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001919662","display_name":"Mowei Wang","orcid":"https://orcid.org/0000-0001-9085-2247"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Mowei Wang","raw_affiliation_strings":["DataCom Production Line, Huawei Technologies"],"raw_orcid":"https://orcid.org/0000-0001-9085-2247","affiliations":[{"raw_affiliation_string":"DataCom Production Line, Huawei Technologies","institution_ids":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078115952","display_name":"Yu Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Yan","raw_affiliation_strings":["China Mobile Research Institute, China Mobile"],"raw_orcid":"https://orcid.org/0009-0006-9986-917X","affiliations":[{"raw_affiliation_string":"China Mobile Research Institute, China Mobile","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110449682","display_name":"Weiqiang Cheng","orcid":"https://orcid.org/0000-0002-4459-8847"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqiang Cheng","raw_affiliation_strings":["China Mobile Research Institute, China Mobile"],"raw_orcid":"https://orcid.org/0000-0002-4459-8847","affiliations":[{"raw_affiliation_string":"China Mobile Research Institute, China Mobile","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013767183","display_name":"Zihan Jiang","orcid":"https://orcid.org/0000-0003-0632-7402"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zihan Jiang","raw_affiliation_strings":["DataCom Production Line, Huawei Technologies"],"raw_orcid":"https://orcid.org/0000-0003-0632-7402","affiliations":[{"raw_affiliation_string":"DataCom Production Line, Huawei Technologies","institution_ids":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027374097","display_name":"Z. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]},{"id":"https://openalex.org/I180895376","display_name":"University of Mobile","ror":"https://ror.org/03sswts20","country_code":"US","type":"education","lineage":["https://openalex.org/I180895376"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhenhui Zhang","raw_affiliation_strings":["China Mobile Research Institute, China Mobile and Department of Computer Science and Technology, Nanjing University"],"raw_orcid":"https://orcid.org/0009-0009-9381-2019","affiliations":[{"raw_affiliation_string":"China Mobile Research Institute, China Mobile and Department of Computer Science and Technology, Nanjing University","institution_ids":["https://openalex.org/I180662265","https://openalex.org/I180895376"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7097756266593933},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.6504127979278564},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.647139310836792},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.6062296032905579},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.25701695680618286},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2463996410369873}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7097756266593933},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6504127979278564},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.647139310836792},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.6062296032905579},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.25701695680618286},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2463996410369873}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3748273.3749196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3748273.3749196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Networks for AI Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6804312440","display_name":null,"funder_award_id":"2024YFB2906601","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W4308760184","https://openalex.org/W4385570483","https://openalex.org/W4387321091","https://openalex.org/W4401211704","https://openalex.org/W4408846413"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Modern":[0],"large":[1],"language":[2],"model":[3],"(LLM)":[4],"serving":[5],"systems":[6],"increasingly":[7],"adopt":[8],"a":[9],"prefill-decode":[10],"disaggregation":[11],"architecture":[12],"to":[13,27],"enhance":[14],"inference":[15],"efficiency.":[16],"While":[17],"this":[18,40],"design":[19],"improves":[20],"resource":[21],"utilization,":[22],"it":[23],"introduces":[24],"latency":[25,41],"due":[26],"the":[28],"transfer":[29],"of":[30],"key-value":[31],"(KV)":[32],"cache.":[33],"The":[34],"community":[35],"has":[36],"generally":[37],"assumed":[38],"that":[39],"is":[42],"bandwidth-bound":[43],"and":[44],"can":[45],"be":[46],"effectively":[47],"mitigated":[48],"by":[49],"high-speed":[50],"interconnects.":[51]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
