{"id":"https://openalex.org/W7164046970","doi":"https://doi.org/10.48550/arxiv.2606.09061","title":"Fairness-Aware and Latency-Controllable Scheduling for Chunked-Prefill LLM Serving","display_name":"Fairness-Aware and Latency-Controllable Scheduling for Chunked-Prefill LLM Serving","publication_year":2026,"publication_date":"2026-06-08","ids":{"openalex":"https://openalex.org/W7164046970","doi":"https://doi.org/10.48550/arxiv.2606.09061"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.09061","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09061","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.09061","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138214862","display_name":"Haoxin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Haoxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138277376","display_name":"Jiayi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiayi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057911001","display_name":"Yueshen Xu","orcid":"https://orcid.org/0000-0001-7210-0543"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yueshen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138238683","display_name":"Rui Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.3001999855041504,"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":0.3001999855041504,"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/T12127","display_name":"Software System Performance and Reliability","score":0.14110000431537628,"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/T11424","display_name":"Security and Verification in Computing","score":0.12849999964237213,"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/scheduling","display_name":"Scheduling (production processes)","score":0.7027000188827515},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6722999811172485},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6488000154495239},{"id":"https://openalex.org/keywords/dynamic-priority-scheduling","display_name":"Dynamic priority scheduling","score":0.4860000014305115},{"id":"https://openalex.org/keywords/round-robin-scheduling","display_name":"Round-robin scheduling","score":0.44029998779296875},{"id":"https://openalex.org/keywords/fair-share-scheduling","display_name":"Fair-share scheduling","score":0.42879998683929443},{"id":"https://openalex.org/keywords/fixed-priority-pre-emptive-scheduling","display_name":"Fixed-priority pre-emptive scheduling","score":0.41200000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073999881744385},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.7027000188827515},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6722999811172485},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6488000154495239},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.49880000948905945},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.4860000014305115},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.44589999318122864},{"id":"https://openalex.org/C175893541","wikidata":"https://www.wikidata.org/wiki/Q1196582","display_name":"Round-robin scheduling","level":4,"score":0.44029998779296875},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.42879998683929443},{"id":"https://openalex.org/C122141398","wikidata":"https://www.wikidata.org/wiki/Q5456330","display_name":"Fixed-priority pre-emptive scheduling","level":5,"score":0.41200000047683716},{"id":"https://openalex.org/C119948110","wikidata":"https://www.wikidata.org/wiki/Q7858726","display_name":"Two-level scheduling","level":4,"score":0.37229999899864197},{"id":"https://openalex.org/C32310161","wikidata":"https://www.wikidata.org/wiki/Q666365","display_name":"Earliest deadline first scheduling","level":5,"score":0.3677999973297119},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.349700003862381},{"id":"https://openalex.org/C127456818","wikidata":"https://www.wikidata.org/wiki/Q238879","display_name":"Rate-monotonic scheduling","level":4,"score":0.3465000092983246},{"id":"https://openalex.org/C76774629","wikidata":"https://www.wikidata.org/wiki/Q1146103","display_name":"Deadline-monotonic scheduling","level":5,"score":0.3416000008583069},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.260699987411499},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.09061","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09061","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.09061","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09061","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"are":[5,178],"increasingly":[6],"deployed":[7],"with":[8,117],"highly":[9],"heterogeneous":[10],"workloads,":[11],"chunked-prefill":[12,78],"execution":[13],"has":[14],"emerged":[15],"as":[16],"a":[17,71,84],"mainstream":[18],"serving":[19],"architecture.":[20],"Balancing":[21],"scheduling":[22,75,87,128],"fairness":[23,59],"and":[24,36,53,61,73,97,108,120,133,156,163,173],"latency":[25,63,147,162,176],"stability":[26],"in":[27,186],"such":[28],"environments":[29],"is":[30],"critical;":[31],"otherwise,":[32],"severe":[33],"head-of-line":[34],"blocking":[35],"request":[37],"starvation":[38],"will":[39],"degrade":[40],"user":[41],"experience.":[42],"However,":[43],"existing":[44],"systems":[45],"rely":[46],"on":[47,130],"rigid":[48],"First-Come,":[49],"First-Served":[50],"(FCFS)":[51],"policies":[52],"static":[54,115],"token":[55],"budgets,":[56],"leading":[57],"to":[58,113,152],"degradation":[60],"unpredictable":[62],"jitter.":[64],"To":[65],"address":[66],"these":[67],"issues,":[68],"we":[69,82,102],"propose":[70],"fairness-aware":[72],"latency-controllable":[74],"framework":[76,129],"for":[77],"LLM":[79],"engines.":[80],"Specifically,":[81],"design":[83],"lightweight":[85],"aging-based":[86],"policy":[88,143],"that":[89,168],"dynamically":[90],"calculates":[91],"priorities":[92],"using":[93,136],"accumulated":[94],"waiting":[95],"time":[96],"remaining":[98],"prefill":[99,123,165,171],"work.":[100],"Furthermore,":[101],"develop":[103],"Latency-Prediction-Based":[104],"Request":[105],"Scheduling":[106],"(LPRS)":[107],"Active":[109],"Prefill":[110],"Control":[111],"(APC)":[112],"replace":[114],"budgets":[116],"target-time":[118],"constraints":[119,177],"actively":[121],"regulate":[122],"concurrency.":[124],"We":[125],"evaluated":[126],"our":[127],"NVIDIA":[131],"GPUs":[132],"Ascend":[134],"accelerators":[135],"real-world":[137],"workloads.":[138],"Results":[139],"show":[140],"the":[141,169,174],"aging":[142],"reduces":[144],"mean":[145],"end-to-end":[146],"by":[148],"over":[149],"10\\%":[150],"compared":[151],"FCFS.":[153],"Moreover,":[154],"LPRS":[155],"APC":[157],"significantly":[158],"reduce":[159],"P99":[160],"tail":[161],"suppress":[164],"fragmentation,":[166],"confirming":[167],"structural":[170],"control":[172],"temporal":[175],"fundamentally":[179],"complementary.":[180],"All":[181],"codes":[182],"have":[183],"been":[184],"released":[185],"Github.":[187]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}