{"id":"https://openalex.org/W4414170683","doi":"https://doi.org/10.1109/iwqos65803.2025.11143346","title":"Libra: Novel LLM Token Streaming via Region-Based Task Scheduling and Token Bundling","display_name":"Libra: Novel LLM Token Streaming via Region-Based Task Scheduling and Token Bundling","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W4414170683","doi":"https://doi.org/10.1109/iwqos65803.2025.11143346"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos65803.2025.11143346","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","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/A5003359550","display_name":"Chengjin Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengjin Zhou","raw_affiliation_strings":["College of Computer Science, DISSec, Nankai University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, DISSec, Nankai University,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339589","display_name":"Song Liu","orcid":"https://orcid.org/0000-0002-3046-3335"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Liu","raw_affiliation_strings":["College of Computer Science, DISSec, Nankai University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, DISSec, Nankai University,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061774892","display_name":"Xinjing Yuan","orcid":"https://orcid.org/0000-0002-5103-5866"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinjing Yuan","raw_affiliation_strings":["College of Computer Science, DISSec, Nankai University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, DISSec, Nankai University,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008846211","display_name":"Jianxin Shi","orcid":"https://orcid.org/0000-0002-7687-8480"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxin Shi","raw_affiliation_strings":["College of Computer Science, DISSec, Nankai University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, DISSec, Nankai University,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368674","display_name":"Yuan Zhang","orcid":"https://orcid.org/0000-0001-9682-5231"},"institutions":[{"id":"https://openalex.org/I4391768176","display_name":"State Key Laboratory of Media Convergence and Communication","ror":"https://ror.org/0595ys057","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zhang","raw_affiliation_strings":["Communication University of China,State Key Laboratory of Media Convergence and Communication,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,State Key Laboratory of Media Convergence and Communication,China","institution_ids":["https://openalex.org/I75689368","https://openalex.org/I4391768176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053568911","display_name":"Lingjun Pu","orcid":"https://orcid.org/0000-0002-3063-8887"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingjun Pu","raw_affiliation_strings":["College of Computer Science, DISSec, Nankai University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, DISSec, Nankai University,China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9995999932289124,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.9994999766349792,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9991999864578247,"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/security-token","display_name":"Security token","score":0.8593000173568726},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.646399974822998},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.42969998717308044},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.397599995136261},{"id":"https://openalex.org/keywords/bundle","display_name":"Bundle","score":0.3953000009059906},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.39410001039505005},{"id":"https://openalex.org/keywords/token-passing","display_name":"Token passing","score":0.3808000087738037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8618000149726868},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8593000173568726},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.646399974822998},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.6398000121116638},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4941999912261963},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C2778134712","wikidata":"https://www.wikidata.org/wiki/Q1047307","display_name":"Bundle","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C115067241","wikidata":"https://www.wikidata.org/wiki/Q1639854","display_name":"Token passing","level":3,"score":0.3808000087738037},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3449000120162964},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25380000472068787},{"id":"https://openalex.org/C135135165","wikidata":"https://www.wikidata.org/wiki/Q386456","display_name":"Token bucket","level":3,"score":0.25110000371932983},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos65803.2025.11143346","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2937348036","display_name":null,"funder_award_id":"62172241,62402247","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G872726882","display_name":null,"funder_award_id":"CUC24GT17","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1994926493","https://openalex.org/W2137152139","https://openalex.org/W2152783321","https://openalex.org/W2238366248","https://openalex.org/W4229005866","https://openalex.org/W4283828295","https://openalex.org/W4322718191","https://openalex.org/W4386977707","https://openalex.org/W4387321091","https://openalex.org/W4389500833","https://openalex.org/W4390305682","https://openalex.org/W4391462666","https://openalex.org/W4395020691","https://openalex.org/W4395686786","https://openalex.org/W4400377444","https://openalex.org/W4401176258","https://openalex.org/W4404995266","https://openalex.org/W4408847395"],"related_works":[],"abstract_inverted_index":{"The":[0],"LLM":[1,85,167],"serving":[2,86,106,168],"systems":[3,87,169],"are":[4,77,90],"increasingly":[5],"growing":[6],"in":[7,46,92,116,186,196,209],"popularity,":[8],"as":[9,32,174],"they":[10,89],"provide":[11],"various":[12],"capabilities":[13],"ranging":[14],"from":[15,68],"realtime":[16],"translation":[17],"to":[18,27,61,79,83,131,150,181,212],"AI-driven":[19],"chatbots.":[20],"Recently,":[21],"significant":[22],"effort":[23],"has":[24],"been":[25],"made":[26],"optimize":[28,151],"server-side":[29],"metrics":[30],"such":[31,173],"token":[33,40,129],"generation":[34],"throughput,":[35],"while":[36],"the":[37,63,69,109,114,127,165,187,197],"optimization":[38],"of":[39,95,118,199],"streaming":[41],"is":[42],"simply":[43],"overlooked,":[44],"resulting":[45],"excessive":[47],"network":[48,52,64],"traffic":[49],"and":[50,74,112,121,125,154,177,191],"poor":[51],"utilization.":[53],"In":[54,97,201],"this":[55,98],"paper,":[56],"we":[57,100,138],"introduce":[58],"user":[59,119,152,171,217],"regions":[60,120],"relieve":[62],"issues,":[65],"since":[66],"users":[67],"same":[70],"region":[71],"(e.g.,":[72,88],"universities":[73],"business":[75],"zones)":[76],"likely":[78],"share":[80],"similar":[81],"behaviors":[82],"access":[84],"active":[91],"a":[93,103,147,205],"period":[94],"time).":[96],"context,":[99],"propose":[101],"Libra,":[102],"proxy-cloud":[104],"collaborative":[105],"system,":[107],"where":[108],"cloud":[110],"generates":[111],"bundles":[113],"tokens":[115],"terms":[117],"region-based":[122,142],"proxy":[123],"extracts":[124],"repacks":[126],"received":[128],"bundle":[130],"their":[132],"corresponding":[133],"users.":[134],"At":[135],"its":[136],"core,":[137],"design":[139],"an":[140],"online":[141],"task":[143],"scheduling":[144],"algorithm":[145],"with":[146],"provable":[148],"performance":[149],"QoE":[153],"system":[155],"overhead":[156],"over":[157],"time.":[158],"Our":[159],"evaluations":[160],"show":[161],"that":[162],"Libra":[163],"outperforms":[164],"state-of-the-art":[166],"(without":[170],"regions),":[172],"vLLM,":[175],"VTC":[176],"Andes,":[178],"by":[179],"up":[180],"<tex":[182,192],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[183,193],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$2.1":[184],"\\times$</tex>":[185,195],"Time-Between-Tokens":[188],"(TBT)":[189],"metric":[190],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$78.4":[194],"number":[198],"packets.":[200],"addition,":[202],"it":[203],"achieves":[204],"32.6":[206],"%":[207],"reduction":[208],"TBT":[210],"compared":[211],"other":[213],"alternative":[214],"algorithms":[215],"(with":[216],"regions).":[218]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
