{"id":"https://openalex.org/W7134820901","doi":"https://doi.org/10.48550/arxiv.2603.07917","title":"SageSched: Efficient LLM Scheduling Confronting Demand Uncertainty and Hybridity","display_name":"SageSched: Efficient LLM Scheduling Confronting Demand Uncertainty and Hybridity","publication_year":2026,"publication_date":"2026-03-09","ids":{"openalex":"https://openalex.org/W7134820901","doi":"https://doi.org/10.48550/arxiv.2603.07917"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.07917","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128648036","display_name":"Zhenghao Gan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gan, Zhenghao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128687556","display_name":"Yichen Bao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bao, Yichen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128638740","display_name":"Yifei Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yifei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128634233","display_name":"Chen Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128676251","display_name":"Quan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Quan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128658550","display_name":"Minyi Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Minyi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5128648036"],"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.23309999704360962,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.23309999704360962,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.2125999927520752,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.08739999681711197,"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/inference","display_name":"Inference","score":0.7563999891281128},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6833000183105469},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5782999992370605},{"id":"https://openalex.org/keywords/hybridity","display_name":"Hybridity","score":0.48260000348091125},{"id":"https://openalex.org/keywords/cost-efficiency","display_name":"Cost efficiency","score":0.34200000762939453}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7563999891281128},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6833000183105469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6708999872207642},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C2779367526","wikidata":"https://www.wikidata.org/wiki/Q1253260","display_name":"Hybridity","level":2,"score":0.48260000348091125},{"id":"https://openalex.org/C11644782","wikidata":"https://www.wikidata.org/wiki/Q15401790","display_name":"Cost efficiency","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3416000008583069},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.07917","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.07917","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.07917","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.07917","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"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":{"Efficient":[0],"LLM":[1,10,30,53],"inference":[2,63,72,94],"scheduling":[3,108],"is":[4],"crucial":[5],"for":[6],"user":[7],"experience.":[8],"However,":[9],"inferences":[11],"exhibit":[12],"remarkable":[13],"demand":[14,58],"uncertainty":[15,59],"(with":[16],"unknown":[17],"output":[18],"length":[19],"beforehand)":[20],"and":[21,26,60,81,99],"hybridity":[22,61],"(being":[23],"both":[24,97],"compute":[25,40,98],"memory":[27,100],"intensive).":[28],"Existing":[29],"schedulers":[31],"rely":[32],"on":[33,39],"simple":[34],"heuristics":[35],"or":[36],"focus":[37],"purely":[38],"resource,":[41],"suffering":[42],"suboptimal":[43],"performance.":[44],"In":[45],"this":[46],"work,":[47],"we":[48],"propose":[49],"SageSched,":[50],"an":[51,93,106,132],"efficient":[52],"scheduler":[54],"that":[55,110,128],"properly":[56],"handles":[57],"of":[62,92,135],"workloads.":[64],"SageSched":[65,104,129],"combines":[66],"prompt":[67],"contents":[68],"with":[69,96],"the":[70,88,113,118],"past":[71],"results":[73],"to":[74],"predict":[75],"output-length":[76],"distribution":[77],"in":[78],"a":[79],"light-weight":[80],"also":[82],"accurate":[83],"manner.":[84],"Meanwhile,":[85],"it":[86],"models":[87],"true":[89],"service":[90],"cost":[91,120],"request":[95,119],"aspects":[101],"considered.":[102],"Finally,":[103],"employs":[105],"uncertainty-aware":[107],"policy":[109],"can":[111,130],"yield":[112],"best":[114],"overall":[115],"efficiency":[116,133],"given":[117],"distributions.":[121],"Testbed":[122],"experiments":[123],"over":[124,136],"diverse":[125],"setups":[126],"confirm":[127],"attain":[131],"improvement":[134],"28.7%.":[137]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-03-11T00:00:00"}