{"id":"https://openalex.org/W6968378792","doi":"https://doi.org/10.5281/zenodo.15580572","title":"EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse","display_name":"EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse","publication_year":2025,"publication_date":"2025-06-03","ids":{"openalex":"https://openalex.org/W6968378792","doi":"https://doi.org/10.5281/zenodo.15580572"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.15580572","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15580572","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},"type":"software","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.15580572","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Guo, Tianyu","orcid":"https://orcid.org/0009-0005-2979-4486"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Tianyu","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":"https://orcid.org/0009-0005-2979-4486","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dong, Hande","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong, Hande","raw_affiliation_strings":["Tencent (China)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent (China)","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Leng, Yichong","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leng, Yichong","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Feng","raw_affiliation_strings":["Tencent (China)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent (China)","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lin, Cheater","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin, Cheater","raw_affiliation_strings":["Tencent (China)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent (China)","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao, Nong","orcid":"https://orcid.org/0000-0002-2166-977X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao, Nong","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":"https://orcid.org/0000-0002-2166-977X","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhang, Xianwei","orcid":"https://orcid.org/0000-0003-3507-4299"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Xianwei","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":"https://orcid.org/0000-0003-3507-4299","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/namespace","display_name":"Namespace","score":0.6007000207901001},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5566999912261963},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5436999797821045},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5250999927520752},{"id":"https://openalex.org/keywords/download","display_name":"Download","score":0.4896000027656555},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.48190000653266907},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4510999917984009}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806000113487244},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.6848000288009644},{"id":"https://openalex.org/C2778383056","wikidata":"https://www.wikidata.org/wiki/Q873636","display_name":"Namespace","level":2,"score":0.6007000207901001},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5566999912261963},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.4896000027656555},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.48190000653266907},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4106999933719635},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.39559999108314514},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.35280001163482666},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C138338577","wikidata":"https://www.wikidata.org/wiki/Q756230","display_name":"Directory service","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29249998927116394},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C2778583558","wikidata":"https://www.wikidata.org/wiki/Q771245","display_name":"Code reuse","level":3,"score":0.27309998869895935},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2526000142097473},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.15580572","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15580572","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Software"}],"best_oa_location":{"id":"doi:10.5281/zenodo.15580572","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15580572","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Our":[0],"artifacts":[1],"require":[2],"a":[3,10,47],"NVIDIA":[4],"GPU":[5],"with":[6],"CUDA":[7],"software":[8],"on":[9],"linux":[11],"operating":[12],"system.":[13],"It":[14,43],"also":[15,67],"requires":[16],"to":[17,61],"install":[18,53],"conda":[19,48,88],"software.":[20,55],"Then":[21,80],"we":[22],"pack":[23],"the":[24,28,35,81],"instructions":[25,83],"for":[26],"preparing":[27],"environment":[29],"in":[30],"scripts/setup.sh.":[31],"To":[32],"set":[33],"up":[34],"environment,":[36],"you":[37],"should":[38,84],"just":[39],"run":[40,85],"source":[41],"scripts/setup.sh":[42],"will":[44],"automatically":[45],"create":[46],"env":[49],"named":[50],"\u2018euro_par_artifact\u2019":[51],"and":[52],"required":[54],"Since":[56],"our":[57],"work":[58],"need":[59],"access":[60],"large":[62],"language":[63],"models":[64],"(LLMs),":[65],"it":[66],"download":[68],"four":[69],"LLMs":[70],"(about":[71],"50-60":[72],"GB)":[73],"from":[74],"huggingface":[75],"into":[76],"local":[77],"directory":[78],"\u2018models\u2019.":[79],"following":[82],"within":[86],"this":[87],"env.":[89]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
