{"id":"https://openalex.org/W4402805837","doi":"https://doi.org/10.1145/3688351.3689164","title":"TwinPilots: A New Computing Paradigm for GPU-CPU Parallel LLM Inference","display_name":"TwinPilots: A New Computing Paradigm for GPU-CPU Parallel LLM Inference","publication_year":2024,"publication_date":"2024-09-16","ids":{"openalex":"https://openalex.org/W4402805837","doi":"https://doi.org/10.1145/3688351.3689164"},"language":"en","primary_location":{"id":"doi:10.1145/3688351.3689164","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3688351.3689164","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3688351.3689164?download=true","source":null,"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 17th ACM International Systems and Storage Conference on ZZZ","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3688351.3689164?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113399778","display_name":"Chengye Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chengye Yu","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0005-7670-5247","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417411","display_name":"Tianyu Wang","orcid":"https://orcid.org/0000-0001-7030-1990"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Wang","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-7030-1990","affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101639532","display_name":"Zili Shao","orcid":"https://orcid.org/0000-0002-2173-2847"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zili Shao","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-2173-2847","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101519451","display_name":"Linjie Zhu","orcid":"https://orcid.org/0000-0003-2914-8749"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linjie Zhu","raw_affiliation_strings":["Sangfor Technologies Inc, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2914-8749","affiliations":[{"raw_affiliation_string":"Sangfor Technologies Inc, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085431083","display_name":"Zhou Xu","orcid":"https://orcid.org/0009-0002-7695-5834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Zhou","raw_affiliation_strings":["Sangfor Technologies Inc, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0002-7695-5834","affiliations":[{"raw_affiliation_string":"Sangfor Technologies Inc, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101421445","display_name":"Song Jiang","orcid":"https://orcid.org/0000-0002-1681-9008"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song Jiang","raw_affiliation_strings":["University of Texas at Arlington, Arlington, USA"],"raw_orcid":"https://orcid.org/0000-0002-1681-9008","affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Arlington, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10346","display_name":"Magnetic confinement fusion research","score":0.7307000160217285,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10346","display_name":"Magnetic confinement fusion research","score":0.7307000160217285,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.7056000232696533,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.7014999985694885,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.832233190536499},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6560004353523254},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5044652223587036},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4939942955970764},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4513052701950073},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3352016508579254},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.33218473196029663},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.26369285583496094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12795886397361755},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.10938623547554016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832233190536499},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6560004353523254},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5044652223587036},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4939942955970764},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4513052701950073},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3352016508579254},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.33218473196029663},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26369285583496094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12795886397361755},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.10938623547554016}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3688351.3689164","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3688351.3689164","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3688351.3689164?download=true","source":null,"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 17th ACM International Systems and Storage Conference on ZZZ","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3688351.3689164","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3688351.3689164","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3688351.3689164?download=true","source":null,"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 17th ACM International Systems and Storage Conference on ZZZ","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402805837.pdf"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2913668833","https://openalex.org/W4224308101","https://openalex.org/W4372263604","https://openalex.org/W6810081322"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W1582436825","https://openalex.org/W1996803181","https://openalex.org/W1656096860","https://openalex.org/W2979588510","https://openalex.org/W2095928260","https://openalex.org/W2268149564","https://openalex.org/W1984739956","https://openalex.org/W2763312740"],"abstract_inverted_index":{"When":[0],"trained":[1],"Large":[2],"Language":[3],"Models":[4],"(LLMs)":[5],"become":[6],"available,":[7],"it":[8],"is":[9,29,32,42],"desirable":[10],"to":[11,73,78,104],"carry":[12],"out":[13],"LLM":[14,27],"inferences":[15],"at":[16,67],"the":[17,34,58,82,92,106],"user":[18],"end":[19],"with":[20,96],"limited":[21],"resources.":[22],"A":[23],"common":[24],"belief":[25,51],"on":[26],"inference":[28],"that":[30,45,60,100],"GPU":[31,46,61],"essentially":[33],"only":[35],"meaningful":[36,97],"processor":[37,95],"as":[38],"almost":[39],"all":[40],"computation":[41],"tensor":[43],"multiplication":[44],"excels":[47],"in.":[48],"However,":[49],"this":[50],"and":[52,65],"its":[53],"practice":[54],"are":[55],"challenged":[56],"by":[57],"fact":[59],"has":[62],"insufficient":[63],"memory":[64,84],"runs":[66],"a":[68,86,94],"much":[69],"slower":[70],"speed":[71],"due":[72],"constantly":[74],"waiting":[75],"for":[76],"data":[77],"be":[79,102],"loaded":[80],"from":[81],"CPU":[83,93],"via":[85],"slow":[87],"PCIe":[88],"bus.":[89],"This":[90],"makes":[91],"computing":[98],"power":[99],"can":[101],"leveraged":[103],"accelerate":[105],"inference.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
