{"id":"https://openalex.org/W4412889578","doi":"https://doi.org/10.18653/v1/2025.acl-long.1568","title":"Squeezed Attention: Accelerating Long Context Length LLM Inference","display_name":"Squeezed Attention: Accelerating Long Context Length LLM Inference","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889578","doi":"https://doi.org/10.18653/v1/2025.acl-long.1568"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1568","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1568","pdf_url":"https://aclanthology.org/2025.acl-long.1568.pdf","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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1568.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007438902","display_name":"Coleman Hooper","orcid":"https://orcid.org/0000-0002-5890-610X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Coleman Richard Charles Hooper","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085531767","display_name":"Sehoon Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sehoon Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093093892","display_name":"Hiva Mohammadzadeh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiva Mohammadzadeh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Monishwaran Maheswaran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Monishwaran Maheswaran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Sebastian Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"June Paik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"June Paik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033006662","display_name":"Michael W. Mahoney","orcid":"https://orcid.org/0000-0001-7920-4652"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael W. Mahoney","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047285420","display_name":"Kurt Keutzer","orcid":"https://orcid.org/0000-0003-3868-8501"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kurt Keutzer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103894843","display_name":"Amir Gholami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amir Gholami","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"32631","last_page":"32652"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9603000283241272,"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":0.9603000283241272,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9592999815940857,"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":0.9265999794006348,"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":0.6768537759780884},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6393484473228455},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5847985148429871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30500027537345886},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.06620392203330994}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6768537759780884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6393484473228455},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5847985148429871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30500027537345886},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.06620392203330994},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1568","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1568","pdf_url":"https://aclanthology.org/2025.acl-long.1568.pdf","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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1568","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1568","pdf_url":"https://aclanthology.org/2025.acl-long.1568.pdf","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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889578.pdf","grobid_xml":"https://content.openalex.org/works/W4412889578.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Coleman":[0],"Richard":[1],"Charles":[2],"Hooper,":[3],"Sehoon":[4],"Kim,":[5],"Hiva":[6],"Mohammadzadeh,":[7],"Monishwaran":[8],"Maheswaran,":[9],"Sebastian":[10],"Zhao,":[11],"June":[12],"Paik,":[13],"Michael":[14],"W.":[15],"Mahoney,":[16],"Kurt":[17],"Keutzer,":[18],"Amir":[19],"Gholami.":[20],"Proceedings":[21],"of":[22,27],"the":[23,28],"63rd":[24],"Annual":[25],"Meeting":[26],"Association":[29],"for":[30],"Computational":[31],"Linguistics":[32],"(Volume":[33],"1:":[34],"Long":[35],"Papers).":[36],"2025.":[37]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
