{"id":"https://openalex.org/W7140701946","doi":"https://doi.org/10.1145/3788087","title":"Cache Your Prompt When It's Green \u2014 Carbon-Aware Caching for Large Language Model Serving","display_name":"Cache Your Prompt When It's Green \u2014 Carbon-Aware Caching for Large Language Model Serving","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7140701946","doi":"https://doi.org/10.1145/3788087"},"language":"en","primary_location":{"id":"doi:10.1145/3788087","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788087","pdf_url":null,"source":{"id":"https://openalex.org/S4210193547","display_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","issn_l":"2476-1249","issn":["2476-1249"],"is_oa":false,"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":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3788087","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130714187","display_name":"Yuyang Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Yuyang Tian","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0009-0006-5438-1795","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Desen Sun","orcid":"https://orcid.org/0000-0001-8630-7959"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Desen Sun","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0001-8630-7959","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yi Ding","orcid":"https://orcid.org/0000-0003-2757-9182"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Ding","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0003-2757-9182","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038231705","display_name":"Sihang Liu","orcid":"https://orcid.org/0000-0001-9706-6177"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sihang Liu","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0001-9706-6177","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5130714187"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.670959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"1","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12238","display_name":"Green IT and Sustainability","score":0.15150000154972076,"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/T12238","display_name":"Green IT and Sustainability","score":0.15150000154972076,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.11129999905824661,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.10339999943971634,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6589000225067139},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5004000067710876},{"id":"https://openalex.org/keywords/carbon-fibers","display_name":"Carbon fibers","score":0.49380001425743103},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4510999917984009},{"id":"https://openalex.org/keywords/carbon-flux","display_name":"Carbon flux","score":0.42570000886917114},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.3880000114440918},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.3734000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7102000117301941},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6589000225067139},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5004000067710876},{"id":"https://openalex.org/C140205800","wikidata":"https://www.wikidata.org/wiki/Q5860","display_name":"Carbon fibers","level":3,"score":0.49380001425743103},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C2993678126","wikidata":"https://www.wikidata.org/wiki/Q167751","display_name":"Carbon flux","level":3,"score":0.42570000886917114},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3456999957561493},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C22607594","wikidata":"https://www.wikidata.org/wiki/Q5375150","display_name":"Enabling","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C134560507","wikidata":"https://www.wikidata.org/wiki/Q753291","display_name":"Environmental economics","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3788087","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788087","pdf_url":null,"source":{"id":"https://openalex.org/S4210193547","display_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","issn_l":"2476-1249","issn":["2476-1249"],"is_oa":false,"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":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3788087","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788087","pdf_url":null,"source":{"id":"https://openalex.org/S4210193547","display_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","issn_l":"2476-1249","issn":["2476-1249"],"is_oa":false,"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":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1986697120","https://openalex.org/W2035097365","https://openalex.org/W2112053513","https://openalex.org/W2128953860","https://openalex.org/W2135916267","https://openalex.org/W2963339397","https://openalex.org/W4281971810","https://openalex.org/W4283384652","https://openalex.org/W4318541641","https://openalex.org/W4366564134","https://openalex.org/W4382142107","https://openalex.org/W4385481862","https://openalex.org/W4387321091","https://openalex.org/W4388264823","https://openalex.org/W4388725043","https://openalex.org/W4389523830","https://openalex.org/W4390189088","https://openalex.org/W4393156812","https://openalex.org/W4401176373","https://openalex.org/W4401211558","https://openalex.org/W4401284706","https://openalex.org/W4402671950","https://openalex.org/W4402835459","https://openalex.org/W4404088343","https://openalex.org/W4408844835","https://openalex.org/W4408848702","https://openalex.org/W4408893361","https://openalex.org/W4409248734","https://openalex.org/W4409561795","https://openalex.org/W4411346229","https://openalex.org/W4411486151","https://openalex.org/W4413397439","https://openalex.org/W4415968362"],"related_works":[],"abstract_inverted_index":{"As":[0,70],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"become":[5],"widely":[6],"used,":[7],"their":[8],"environmental":[9],"impact":[10],"\u2014":[11,15],"especially":[12],"carbon":[13,25,51,65,75,106,123,138],"emission":[14,107,124],"has":[16],"attracted":[17],"more":[18],"attention.":[19],"Prior":[20],"studies":[21],"focus":[22],"on":[23],"compute-related":[24],"emissions.":[26],"In":[27],"this":[28,57,82],"paper,":[29],"we":[30,84],"find":[31],"that":[32,92,133],"storage":[33,77],"is":[34],"another":[35],"key":[36],"contributor.":[37],"LLM":[38,99],"caching,":[39],"which":[40],"saves":[41],"and":[42,108,122],"reuses":[43],"KV":[44],"caches":[45],"for":[46,98,161],"repeated":[47],"context,":[48],"reduces":[49],"operational":[50],"by":[52],"avoiding":[53],"redundant":[54],"computation.":[55],"However,":[56],"benefit":[58],"comes":[59],"at":[60],"the":[61,73,103,112,118,147],"cost":[62],"of":[63,76,140,164],"embodied":[64,74],"from":[66,129],"high-capacity,":[67],"high-speed":[68],"SSDs.":[69],"LLMs":[71],"scale,":[72],"grows":[78],"significantly.":[79],"To":[80],"address":[81],"tradeoff,":[83],"present":[85],"GreenCache,":[86],"a":[87],"carbon-aware":[88],"cache":[89],"management":[90],"framework":[91],"dynamically":[93],"derives":[94],"resource":[95,113],"allocation":[96],"plans":[97],"serving.":[100],"GreenCache":[101,134],"analyzes":[102],"correlation":[104],"between":[105,120],"SLO":[109,121],"satisfaction,":[110],"reconfiguring":[111],"over":[114],"time":[115],"to":[116,154],"keep":[117],"balance":[119],"under":[125],"dynamic":[126],"workloads.":[127],"Evaluations":[128],"real":[130],"traces":[131],"demonstrate":[132],"achieves":[135],"an":[136],"average":[137],"reduction":[139],"15.1%":[141],"when":[142],"serving":[143],"Llama-3":[144],"70B":[145],"in":[146],"FR":[148],"grid,":[149],"with":[150],"reductions":[151],"reaching":[152],"up":[153],"25.3%,":[155],"while":[156],"staying":[157],"within":[158],"latency":[159],"constraints":[160],">":[162],"90%":[163],"requests.":[165]},"counts_by_year":[],"updated_date":"2026-03-28T06:11:35.319607","created_date":"2026-03-27T00:00:00"}