{"id":"https://openalex.org/W4415332981","doi":"https://doi.org/10.1145/3803390","title":"Hermes: Efficient Serving of LLM Applications with Probabilistic Demand Modeling","display_name":"Hermes: Efficient Serving of LLM Applications with Probabilistic Demand Modeling","publication_year":2026,"publication_date":"2026-04-07","ids":{"openalex":"https://openalex.org/W4415332981","doi":"https://doi.org/10.1145/3803390"},"language":"en","primary_location":{"id":"doi:10.1145/3803390","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803390","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1145/3803390","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100352572","display_name":"Yifei Liu","orcid":"https://orcid.org/0009-0005-7427-0024"},"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":"Yifei Liu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0009-0004-1328-8119","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120057012","display_name":"Zuo Gan","orcid":null},"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":"Zuo Gan","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0009-0008-8285-2499","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120057013","display_name":"Zhenghao Gan","orcid":null},"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":"Zhenghao Gan","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0009-0008-3006-1943","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016586261","display_name":"W. Wang","orcid":null},"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"],"raw_orcid":"https://orcid.org/0009-0006-5548-9458","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111598130","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0002-4971-5029"},"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"],"raw_orcid":"https://orcid.org/0000-0001-9480-5632","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yizhou Shan","orcid":"https://orcid.org/0009-0007-9519-0546"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yizhou Shan","raw_affiliation_strings":["Huawei Technologies Co Ltd"],"raw_orcid":"https://orcid.org/0009-0007-9519-0546","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082739849","display_name":"Xusheng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xusheng Chen","raw_affiliation_strings":["Huawei Technologies Co Ltd"],"raw_orcid":"https://orcid.org/0000-0002-2807-9780","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenhua Han","orcid":"https://orcid.org/0000-0002-2880-7100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenhua Han","raw_affiliation_strings":["Unaffiliated"],"raw_orcid":"https://orcid.org/0000-0002-2880-7100","affiliations":[{"raw_affiliation_string":"Unaffiliated","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yifei Zhu","orcid":"https://orcid.org/0000-0003-4352-6507"},"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":"Yifei Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0000-0003-4352-6507","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shixuan Sun","orcid":"https://orcid.org/0000-0003-4060-9438"},"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":"Shixuan Sun","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0000-0003-4060-9438","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"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":["Computer Science, Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0000-0003-0034-2302","affiliations":[{"raw_affiliation_string":"Computer Science, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00607405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"2","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12146","display_name":"Power Line Communications and Noise","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12146","display_name":"Power Line Communications and Noise","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9708999991416931,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11409","display_name":"Advanced Wireless Network Optimization","score":0.9100000262260437,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.782800018787384},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6155999898910522},{"id":"https://openalex.org/keywords/queueing-theory","display_name":"Queueing theory","score":0.5633999705314636},{"id":"https://openalex.org/keywords/on-demand","display_name":"On demand","score":0.4422999918460846},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4106999933719635},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.34360000491142273}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.782800018787384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803000211715698},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6155999898910522},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C2983523559","wikidata":"https://www.wikidata.org/wiki/Q410657","display_name":"On demand","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.41929998993873596},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4106999933719635},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C13736549","wikidata":"https://www.wikidata.org/wiki/Q4489420","display_name":"Industrial engineering","level":1,"score":0.32260000705718994},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.3125},{"id":"https://openalex.org/C2777958785","wikidata":"https://www.wikidata.org/wiki/Q17120940","display_name":"Resource efficiency","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28029999136924744},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.26930001378059387},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.2565999925136566}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3803390","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803390","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2506.14851","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.14851","pdf_url":"https://arxiv.org/pdf/2506.14851","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"text"},{"id":"pmh:oai:arXiv.org:2506.14851","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.14851","pdf_url":"https://arxiv.org/pdf/2506.14851","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.14851","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.14851","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":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3803390","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803390","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G13189788","display_name":null,"funder_award_id":"62572304","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2140519736","https://openalex.org/W4393160302","https://openalex.org/W7133227460","https://openalex.org/W3095319910","https://openalex.org/W2499002200","https://openalex.org/W4318541676","https://openalex.org/W4309674289","https://openalex.org/W4389519928","https://openalex.org/W4387321091","https://openalex.org/W4388994228","https://openalex.org/W4404386015","https://openalex.org/W2798515322","https://openalex.org/W2028301248","https://openalex.org/W2087309216","https://openalex.org/W4404401017"],"related_works":[],"abstract_inverted_index":{"Applications":[0],"based":[1],"on":[2,24],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"contain":[7],"a":[8,38,66],"series":[9],"of":[10,34,59,86],"tasks":[11],"to":[12,44,98,117],"address":[13],"real-world":[14],"problems":[15],"with":[16,71,126],"boosted":[17],"capability,":[18],"which":[19,80],"have":[20],"dynamic":[21],"demand":[22,91],"volumes":[23],"diverse":[25,127],"backends.":[26],"Existing":[27],"serving":[28,85,138],"systems":[29],"treat":[30],"the":[31,56,95,100,106,114,136,141,149],"resource":[32,57],"demands":[33,58],"LLM":[35,60,87,128],"applications":[36,61,129],"as":[37],"blackbox,":[39],"compromising":[40],"end-to-end":[41],"efficiency":[42],"due":[43],"improper":[45],"queuing":[46],"order":[47,102],"and":[48,68,148],"backend":[49],"warm":[50],"up":[51],"latency.":[52],"We":[53,76],"find":[54],"that":[55,103,131],"can":[62,104,133],"be":[63],"modeled":[64],"in":[65],"general":[67],"accurate":[69],"manner":[70],"Probabilistic":[72],"Demand":[73],"Graph":[74],"(PDGraph).":[75],"then":[77],"propose":[78],"Hermes,":[79],"leverages":[81],"PDGraph":[82,115],"for":[83],"efficient":[84],"applications.":[88],"Confronting":[89],"probabilistic":[90],"description,":[92],"Hermes":[93,132],"applies":[94],"Gittins":[96],"policy":[97],"determine":[99],"scheduling":[101],"minimize":[105],"average":[107,142],"application":[108,137],"completion":[109,143,151],"time.":[110],"It":[111],"also":[112],"uses":[113],"model":[116],"help":[118],"prewarm":[119],"cold":[120],"backends":[121],"at":[122],"proper":[123],"moments.":[124],"Experiments":[125],"confirm":[130],"effectively":[134],"improve":[135],"efficiency,":[139],"reducing":[140],"time":[144,152],"by":[145,153],"over":[146,154],"70%":[147],"P95":[150],"80%.":[155]},"counts_by_year":[],"updated_date":"2026-07-03T06:15:21.484131","created_date":"2025-10-19T00:00:00"}
