{"id":"https://openalex.org/W4408903522","doi":"https://doi.org/10.1145/3676641.3715996","title":"POD-A <scp>ttention</scp> : Unlocking Full Prefill-Decode Overlap for Faster LLM Inference","display_name":"POD-A <scp>ttention</scp> : Unlocking Full Prefill-Decode Overlap for Faster LLM Inference","publication_year":2025,"publication_date":"2025-03-27","ids":{"openalex":"https://openalex.org/W4408903522","doi":"https://doi.org/10.1145/3676641.3715996"},"language":"en","primary_location":{"id":"doi:10.1145/3676641.3715996","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676641.3715996","pdf_url":null,"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 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3676641.3715996","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041172518","display_name":"Aditya K. Kamath","orcid":"https://orcid.org/0000-0001-6565-3764"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya K. Kamath","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6565-3764","affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069996639","display_name":"Ramya Prabhu","orcid":"https://orcid.org/0009-0002-7266-5522"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ramya Prabhu","raw_affiliation_strings":["Microsoft Research, Bengaluru, India"],"raw_orcid":"https://orcid.org/0009-0002-7266-5522","affiliations":[{"raw_affiliation_string":"Microsoft Research, Bengaluru, India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005136390","display_name":"Jayashree Mohan","orcid":"https://orcid.org/0009-0005-5260-3203"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jayashree Mohan","raw_affiliation_strings":["Microsoft Research, Bengaluru, India"],"raw_orcid":"https://orcid.org/0009-0005-5260-3203","affiliations":[{"raw_affiliation_string":"Microsoft Research, Bengaluru, India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048629969","display_name":"Simon Peter","orcid":"https://orcid.org/0009-0007-4748-8524"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simon Peter","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0009-0007-4748-8524","affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015355530","display_name":"Ramachandran Ramjee","orcid":"https://orcid.org/0000-0003-0007-6040"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ramachandran Ramjee","raw_affiliation_strings":["Microsoft Research, Bengaluru, India"],"raw_orcid":"https://orcid.org/0000-0003-0007-6040","affiliations":[{"raw_affiliation_string":"Microsoft Research, Bengaluru, India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060296906","display_name":"Ashish Panwar","orcid":"https://orcid.org/0009-0007-0621-4412"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashish Panwar","raw_affiliation_strings":["Microsoft Research, Bengaluru, India"],"raw_orcid":"https://orcid.org/0009-0007-0621-4412","affiliations":[{"raw_affiliation_string":"Microsoft Research, Bengaluru, India","institution_ids":["https://openalex.org/I4210124949"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.3465,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.99129016,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"897","last_page":"912"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.995199978351593,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.995199978351593,"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/T10028","display_name":"Topic Modeling","score":0.983299970626831,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6197919845581055},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5758519172668457},{"id":"https://openalex.org/keywords/point-of-delivery","display_name":"Point of delivery","score":0.4633842706680298},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.37728679180145264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1498628854751587}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6197919845581055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5758519172668457},{"id":"https://openalex.org/C137776501","wikidata":"https://www.wikidata.org/wiki/Q7208270","display_name":"Point of delivery","level":2,"score":0.4633842706680298},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.37728679180145264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1498628854751587},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3676641.3715996","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676641.3715996","pdf_url":null,"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 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3676641.3715996","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676641.3715996","pdf_url":null,"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 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G556043646","display_name":null,"funder_award_id":"2212580","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":22,"referenced_works":["https://openalex.org/W1968391520","https://openalex.org/W2018201741","https://openalex.org/W2023415862","https://openalex.org/W2098274770","https://openalex.org/W2106329447","https://openalex.org/W2134427337","https://openalex.org/W2152517358","https://openalex.org/W2323693848","https://openalex.org/W2582905775","https://openalex.org/W2914304175","https://openalex.org/W3193985311","https://openalex.org/W4220818654","https://openalex.org/W4312060029","https://openalex.org/W4312901420","https://openalex.org/W4321446237","https://openalex.org/W4387321091","https://openalex.org/W4392265896","https://openalex.org/W4401211704","https://openalex.org/W4404401017","https://openalex.org/W4404401018","https://openalex.org/W4407217670","https://openalex.org/W6608548112"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1480038316","https://openalex.org/W4383033865","https://openalex.org/W3142541575","https://openalex.org/W2375444032","https://openalex.org/W4313588295","https://openalex.org/W2352729895","https://openalex.org/W2329675728"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-03-28T00:00:00"}