{"id":"https://openalex.org/W4402897396","doi":"https://doi.org/10.1109/iwqos61813.2024.10682929","title":"Towards Efficient Compound Large Language Model System Serving in the Wild","display_name":"Towards Efficient Compound Large Language Model System Serving in the Wild","publication_year":2024,"publication_date":"2024-06-19","ids":{"openalex":"https://openalex.org/W4402897396","doi":"https://doi.org/10.1109/iwqos61813.2024.10682929"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos61813.2024.10682929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos61813.2024.10682929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"},"type":"article","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/A5100515623","display_name":"Yifei Zhu","orcid":"https://orcid.org/0009-0005-6584-2684"},"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":true,"raw_author_name":"Yifei Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University,UM-SJTU Joint Institute"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,UM-SJTU Joint Institute","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055286613","display_name":"Botao Zhu","orcid":"https://orcid.org/0000-0001-6639-4186"},"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":"Botao Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University,UM-SJTU Joint Institute"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,UM-SJTU Joint Institute","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418575","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-4273-7521"},"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,John Hopcroft Center"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,John Hopcroft Center","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107533503","display_name":"Xiaoyi Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyi Fan","raw_affiliation_strings":["Jiangxing Intelligence Inc"],"affiliations":[{"raw_affiliation_string":"Jiangxing Intelligence Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100515623"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67164179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9283000230789185,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9283000230789185,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9276000261306763,"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/computer-science","display_name":"Computer science","score":0.6402572393417358},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4777071475982666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6402572393417358},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4777071475982666}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos61813.2024.10682929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos61813.2024.10682929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":8,"referenced_works":["https://openalex.org/W4388626886","https://openalex.org/W4393160302","https://openalex.org/W6798182279","https://openalex.org/W6850625674","https://openalex.org/W6851513886","https://openalex.org/W6853325866","https://openalex.org/W6854908924","https://openalex.org/W6858988530"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Utilizing":[0],"compound":[1,28,61,80],"Large":[2],"Language":[3],"Model":[4],"(LLM)":[5],"systems,":[6,30],"instead":[7],"of":[8,24,89],"a":[9,16,21,70],"monolithic":[10],"LLM":[11,29,32,62,81],"model,":[12],"is":[13],"gradually":[14],"becoming":[15],"practical":[17],"solution":[18],"to":[19,41,74],"realize":[20],"diverse":[22],"range":[23],"industry":[25],"applications.":[26],"In":[27,45],"an":[31],"collaborates":[33],"with":[34],"other":[35],"external":[36],"tools,":[37],"APIs,":[38],"or":[39],"LLMs":[40],"offer":[42],"intelligent":[43],"services.":[44],"this":[46],"poster,":[47],"we":[48],"identify":[49],"the":[50],"unique":[51],"challenges,":[52],"namely":[53],"temporal":[54],"and":[55],"topological":[56],"uncertainty,":[57],"brought":[58],"about":[59],"by":[60],"systems":[63],"in":[64,78],"system":[65],"serving.":[66],"We":[67],"then":[68],"propose":[69],"priority-based":[71],"scheduling":[72,91],"policy":[73],"schedule":[75],"different":[76],"stages":[77],"DAG-represented":[79],"systems.":[82],"The":[83],"preliminary":[84],"results":[85],"show":[86],"promising":[87],"performance":[88],"uncertainty-aware":[90],"policies.":[92]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}