{"id":"https://openalex.org/W7167090265","doi":"https://doi.org/10.1145/3797905.3807874","title":"Latency-SLO-Aware Memory Offloading for Large Language Model Inference","display_name":"Latency-SLO-Aware Memory Offloading for Large Language Model Inference","publication_year":2026,"publication_date":"2026-07-02","ids":{"openalex":"https://openalex.org/W7167090265","doi":"https://doi.org/10.1145/3797905.3807874"},"language":null,"primary_location":{"id":"doi:10.1145/3797905.3807874","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3807874","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3797905.3807874","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033914326","display_name":"Chenxiang Ma","orcid":"https://orcid.org/0000-0003-2065-7571"},"institutions":[{"id":"https://openalex.org/I4210139765","display_name":"Beijing Computing Center","ror":"https://ror.org/047r47y76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210139765"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxiang Ma","raw_affiliation_strings":["Peking University, Beijing, Beijing, China and Alibaba Cloud Computing, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-3439-6084","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, China and Alibaba Cloud Computing, Beijing, Beijing, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I4210139765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101987114","display_name":"Hanyu Zhao","orcid":"https://orcid.org/0000-0002-2536-0016"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyu Zhao","raw_affiliation_strings":["Alibaba Cloud Computing, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-2536-0016","affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103041352","display_name":"Zhisheng Ye","orcid":"https://orcid.org/0000-0002-4568-0244"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhisheng Ye","raw_affiliation_strings":["Peking University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4568-0244","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008525373","display_name":"Zehua Yang","orcid":"https://orcid.org/0000-0001-9672-8204"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehua Yang","raw_affiliation_strings":["Peking University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8077-6356","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048237122","display_name":"Tianhao Fu","orcid":"https://orcid.org/0000-0001-9084-7165"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhao Fu","raw_affiliation_strings":["Peking University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9084-7165","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034229001","display_name":"Han Jl","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxun Han","raw_affiliation_strings":["Peking University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-4900-6874","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436779","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0002-6299-4683"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["Peking University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6299-4683","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028194980","display_name":"Yingwei Luo","orcid":"https://orcid.org/0000-0002-7903-0717"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingwei Luo","raw_affiliation_strings":["Peking University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7903-0717","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395154","display_name":"Xiaolin Wang","orcid":"https://orcid.org/0000-0002-6951-1613"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Wang","raw_affiliation_strings":["Peking University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6951-1613","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925944","display_name":"Zhenlin Wang","orcid":"https://orcid.org/0000-0002-0429-4371"},"institutions":[{"id":"https://openalex.org/I11957088","display_name":"Michigan Technological University","ror":"https://ror.org/0036rpn28","country_code":"US","type":"education","lineage":["https://openalex.org/I11957088"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenlin Wang","raw_affiliation_strings":["Michigan Technological University, Houghton, Michigan, USA"],"raw_orcid":"https://orcid.org/0000-0002-0429-4371","affiliations":[{"raw_affiliation_string":"Michigan Technological University, Houghton, Michigan, USA","institution_ids":["https://openalex.org/I11957088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139875263","display_name":"Yong Li","orcid":"https://orcid.org/0000-0001-9072-3170"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Li","raw_affiliation_strings":["Alibaba Cloud Computing, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9072-3170","affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing, Beijing, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045275286","display_name":"Diyu Zhou","orcid":"https://orcid.org/0009-0003-8620-1064"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Diyu Zhou","raw_affiliation_strings":["Peking University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-8620-1064","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":"919","last_page":"932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.11739999800920486,"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/T14347","display_name":"Big Data and Digital Economy","score":0.11739999800920486,"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/T10028","display_name":"Topic Modeling","score":0.08540000021457672,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.06310000270605087,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.5774000287055969},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5199000239372253},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4422000050544739},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.4058000147342682},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.3416000008583069}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914000153541565},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5774000287055969},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.4058000147342682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3596000075340271},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29980000853538513},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.2922999858856201},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.27149999141693115}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797905.3807874","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3807874","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3797905.3807874","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3807874","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W4321636575","https://openalex.org/W4324292875","https://openalex.org/W4386730038","https://openalex.org/W4387321091","https://openalex.org/W4389209096","https://openalex.org/W4389523621","https://openalex.org/W4390263770","https://openalex.org/W4401211704","https://openalex.org/W4402409840","https://openalex.org/W4402671659","https://openalex.org/W4402683942","https://openalex.org/W4404386015","https://openalex.org/W4404726321","https://openalex.org/W4408895130","https://openalex.org/W4409047785","https://openalex.org/W4409248688","https://openalex.org/W4412875469","https://openalex.org/W4413757113","https://openalex.org/W4415797413"],"related_works":[],"abstract_inverted_index":{"Offloading":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"states":[5],"to":[6,12,49],"host":[7,55],"memory":[8,31,67],"during":[9],"inference":[10],"promises":[11],"reduce":[13],"operational":[14],"costs":[15],"by":[16],"supporting":[17],"larger":[18,23],"models,":[19],"longer":[20],"prompts,":[21],"and":[22,61],"batch":[24],"sizes.":[25],"However,":[26],"the":[27,64],"design":[28],"of":[29,66],"existing":[30],"offloading":[32],"mechanisms":[33],"does":[34],"not":[35],"take":[36],"latency":[37],"service-level":[38],"objectives":[39],"(SLOs)":[40],"into":[41],"consideration.":[42],"As":[43],"a":[44],"result,":[45],"they":[46],"either":[47],"lead":[48],"frequent":[50],"SLO":[51],"violations":[52],"or":[53],"underutilize":[54],"memory,":[56],"thereby":[57],"incurring":[58],"economic":[59],"loss":[60],"thus":[62],"defeating":[63],"purpose":[65],"offloading.":[68]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-03T00:00:00"}
