{"id":"https://openalex.org/W4403337152","doi":"https://doi.org/10.1145/3656019.3676945","title":"Activation Sequence Caching: High-Throughput and Memory-Efficient Generative Inference with a Single GPU","display_name":"Activation Sequence Caching: High-Throughput and Memory-Efficient Generative Inference with a Single GPU","publication_year":2024,"publication_date":"2024-10-11","ids":{"openalex":"https://openalex.org/W4403337152","doi":"https://doi.org/10.1145/3656019.3676945"},"language":"en","primary_location":{"id":"doi:10.1145/3656019.3676945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3656019.3676945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Parallel Architectures and Compilation Techniques","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/A5046774082","display_name":"Sowoong Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sowoong Kim","raw_affiliation_strings":["UNIST, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"UNIST, Republic of Korea","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109027354","display_name":"Eunyeong Sim","orcid":null},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eunyeong Sim","raw_affiliation_strings":["UNIST, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"UNIST, Republic of Korea","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008996226","display_name":"Youngsam Shin","orcid":"https://orcid.org/0009-0000-6978-5780"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngsam Shin","raw_affiliation_strings":["Samsung Advanced Institute of Technology, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061159627","display_name":"Yeongon Cho","orcid":"https://orcid.org/0009-0002-1242-6343"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"YeonGon Cho","raw_affiliation_strings":["Samsung Advanced Institute of Technology, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071289684","display_name":"Woongki Baek","orcid":"https://orcid.org/0000-0002-1877-7307"},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woongki Baek","raw_affiliation_strings":["UNIST, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"UNIST, Republic of Korea","institution_ids":["https://openalex.org/I48566637"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5046774082"],"corresponding_institution_ids":["https://openalex.org/I48566637"],"apc_list":null,"apc_paid":null,"fwci":0.3415,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67099154,"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":"78","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9966999888420105,"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/T10028","display_name":"Topic Modeling","score":0.9966999888420105,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9961000084877014,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9871000051498413,"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/computer-science","display_name":"Computer science","score":0.7960613965988159},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.7381482720375061},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7135686874389648},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6374408006668091},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5973588228225708},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.43761885166168213},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34118926525115967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3283005952835083},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16298317909240723}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7960613965988159},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.7381482720375061},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7135686874389648},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6374408006668091},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5973588228225708},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.43761885166168213},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34118926525115967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3283005952835083},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16298317909240723},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3656019.3676945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3656019.3676945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G7113188890","display_name":null,"funder_award_id":"NRF-2021R1A2C1011482","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1493774699","https://openalex.org/W2489529491","https://openalex.org/W2560674852","https://openalex.org/W2798707674","https://openalex.org/W2912500072","https://openalex.org/W2912506132","https://openalex.org/W2914209329","https://openalex.org/W2969388332","https://openalex.org/W2982225306","https://openalex.org/W2984200518","https://openalex.org/W2991040477","https://openalex.org/W3010830594","https://openalex.org/W3012479151","https://openalex.org/W3012514909","https://openalex.org/W3090303800","https://openalex.org/W3157864729","https://openalex.org/W3204998121","https://openalex.org/W3205504880","https://openalex.org/W3205803342","https://openalex.org/W4289646389","https://openalex.org/W4301361180","https://openalex.org/W4318328313","https://openalex.org/W4321636575","https://openalex.org/W4321636758","https://openalex.org/W4380769213"],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W2136583354","https://openalex.org/W2111238207","https://openalex.org/W4390718435","https://openalex.org/W2055243143","https://openalex.org/W4390549206","https://openalex.org/W3137171911","https://openalex.org/W4379540039","https://openalex.org/W2760721665","https://openalex.org/W4237784285"],"abstract_inverted_index":{"Generative":[0,16],"artificial":[1],"intelligence":[2],"is":[3],"widely":[4],"used":[5],"for":[6,67],"various":[7],"tasks":[8],"such":[9],"as":[10],"language":[11],"translation":[12],"and":[13,21,34,52,64],"art":[14],"creation.":[15],"inference":[17,42,89],"employs":[18],"the":[19,29,32,39,50,56,62,70,74],"key":[20,51,63],"value":[22,53,65],"tensors":[23,54,66],"to":[24,59,96],"encode":[25],"relational":[26],"information":[27],"among":[28],"tokens":[30],"in":[31],"input":[33],"output":[35],"sequences.":[36],"Most":[37],"of":[38,69,77,81],"existing":[40],"generative":[41,88],"frameworks":[43],"use":[44,76],"KV":[45,57],"caching":[46],"(KVC),":[47],"which":[48,86],"caches":[49],"(i.e.,":[55],"cache)":[58],"avoid":[60],"recomputing":[61],"each":[68],"processed":[71],"tokens.":[72],"Despite":[73],"widespread":[75],"KVC,":[78],"in-depth":[79],"characterization":[80],"KVC":[82],"with":[83,90],"tensor":[84],"offloading,":[85],"enables":[87],"a":[91],"single":[92],"GPU,":[93],"remains":[94],"yet":[95],"be":[97],"explored.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}