{"id":"https://openalex.org/W7169827217","doi":"https://doi.org/10.1145/3820441.3820479","title":"Towards Efficient Serving of Network-intensive LLM Inferences","display_name":"Towards Efficient Serving of Network-intensive LLM Inferences","publication_year":2026,"publication_date":"2026-07-21","ids":{"openalex":"https://openalex.org/W7169827217","doi":"https://doi.org/10.1145/3820441.3820479"},"language":null,"primary_location":{"id":"doi:10.1145/3820441.3820479","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3820441.3820479","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 10th Asia-Pacific Workshop on Networking","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3820441.3820479","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5141301276","display_name":"Weiye Wang","orcid":"https://orcid.org/0009-0006-5548-9458"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiye Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-5548-9458","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418393","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0001-9480-5632"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9480-5632","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071584772","display_name":"Junxue Zhang","orcid":"https://orcid.org/0000-0001-6926-7801"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junxue Zhang","raw_affiliation_strings":["University of Science and Technology of China, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9859-2045","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Shanghai, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I148128674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036552819","display_name":"Zhusheng Wang","orcid":"https://orcid.org/0000-0002-8086-6036"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhusheng Wang","raw_affiliation_strings":["Huawei, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8086-6036","affiliations":[{"raw_affiliation_string":"Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134511260","display_name":"Hui Yuan","orcid":"https://orcid.org/0009-0005-5352-1277"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Yuan","raw_affiliation_strings":["Huawei, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-5352-1277","affiliations":[{"raw_affiliation_string":"Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033181343","display_name":"Zixuan Guan","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Guan","raw_affiliation_strings":["Huawei, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-3780-1203","affiliations":[{"raw_affiliation_string":"Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060249411","display_name":"Xiaolong Zheng","orcid":"https://orcid.org/0000-0001-7950-6773"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Zheng","raw_affiliation_strings":["Huawei, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-9549-186X","affiliations":[{"raw_affiliation_string":"Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002653936","display_name":"Qizhen Weng","orcid":"https://orcid.org/0000-0001-9195-6443"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qizhen Weng","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9195-6443","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046212412","display_name":"Yin Chen","orcid":"https://orcid.org/0000-0002-0367-4276"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Chen","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-4930-1028","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minyi Guo","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0034-2302","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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":"260","last_page":"266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6391000151634216},{"id":"https://openalex.org/keywords/ignorance","display_name":"Ignorance","score":0.5400999784469604},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5324000120162964},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5256999731063843},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.4593999981880188},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.38670000433921814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7163000106811523},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6391000151634216},{"id":"https://openalex.org/C2778732403","wikidata":"https://www.wikidata.org/wiki/Q815577","display_name":"Ignorance","level":2,"score":0.5400999784469604},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5324000120162964},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5256999731063843},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.35929998755455017},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33219999074935913},{"id":"https://openalex.org/C120524526","wikidata":"https://www.wikidata.org/wiki/Q1709148","display_name":"Reboot","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2578999996185303},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3820441.3820479","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3820441.3820479","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 10th Asia-Pacific Workshop on Networking","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3820441.3820479","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3820441.3820479","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 10th Asia-Pacific Workshop on Networking","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2057178544","https://openalex.org/W2109488193","https://openalex.org/W3095319910","https://openalex.org/W4318541537","https://openalex.org/W4387321091","https://openalex.org/W4388994228","https://openalex.org/W4389209096","https://openalex.org/W4399795308","https://openalex.org/W4401176373","https://openalex.org/W4402671258","https://openalex.org/W4409739675","https://openalex.org/W4412889920","https://openalex.org/W4414736234","https://openalex.org/W4414834420","https://openalex.org/W4415797413","https://openalex.org/W4415797534"],"related_works":[],"abstract_inverted_index":{"Prefix":[0],"caching":[1],"has":[2,34],"become":[3,35],"a":[4],"key":[5],"technique":[6],"for":[7],"LLM":[8,24,42,56],"serving,":[9],"and":[10,78],"nowadays":[11],"the":[12,48],"reusable":[13],"KVCache":[14,32],"contents":[15],"are":[16,44,59,66],"often":[17],"hosted":[18],"on":[19],"distributed":[20],"servers.":[21],"For":[22],"long-context":[23],"inferences":[25,43],"with":[26],"high":[27],"cache":[28],"hit":[29],"ratio,":[30],"cross-server":[31],"transmission":[33],"an":[36],"emerging":[37],"performance":[38],"bottleneck;":[39],"such":[40,71],"network-intensive":[41],"increasingly":[45],"prevalent":[46],"in":[47],"coming":[49],"era":[50],"of":[51,80],"agentic":[52],"AI.":[53],"However,":[54],"existing":[55],"inference":[57],"engines":[58],"essentially":[60],"compute-centric;":[61],"we":[62],"find":[63],"that":[64],"they":[65],"highly":[67],"inefficient":[68],"when":[69],"serving":[70],"workloads":[72],"due":[73],"to":[74],"compute-stage":[75],"service":[76],"blocking":[77],"ignorance":[79],"KVCache-transfer":[81],"cost.":[82]},"counts_by_year":[],"updated_date":"2026-07-22T06:00:27.337203","created_date":"2026-07-22T00:00:00"}
