{"id":"https://openalex.org/W7155527384","doi":"https://doi.org/10.1145/3767295.3769364","title":"SAS: Sparse Attention Synthesizer for Efficient Language Model Inference","display_name":"SAS: Sparse Attention Synthesizer for Efficient Language Model Inference","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W7155527384","doi":"https://doi.org/10.1145/3767295.3769364"},"language":null,"primary_location":{"id":"doi:10.1145/3767295.3769364","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769364","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 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767295.3769364","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134547051","display_name":"Yuan Zhou","orcid":"https://orcid.org/0009-0002-2144-8931"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Zhou","raw_affiliation_strings":["Amazon, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0009-0002-2144-8931","affiliations":[{"raw_affiliation_string":"Amazon, Santa Clara, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032824854","display_name":"Shaojie Xiang","orcid":"https://orcid.org/0000-0002-6901-8837"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaojie Xiang","raw_affiliation_strings":["Amazon, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0000-0002-6901-8837","affiliations":[{"raw_affiliation_string":"Amazon, Santa Clara, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052479606","display_name":"Lingfan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingfan Yu","raw_affiliation_strings":["Amazon, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0009-0008-7711-263X","affiliations":[{"raw_affiliation_string":"Amazon, Santa Clara, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102001024","display_name":"Zhenyu Song","orcid":"https://orcid.org/0000-0003-2386-2271"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenyu Song","raw_affiliation_strings":["Amazon, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0000-0003-2386-2271","affiliations":[{"raw_affiliation_string":"Amazon, Santa Clara, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476447","display_name":"Charith Mendis","orcid":"https://orcid.org/0000-0002-8140-2321"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charith Mendis","raw_affiliation_strings":["Amazon, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0000-0002-8140-2321","affiliations":[{"raw_affiliation_string":"Amazon, Santa Clara, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101638214","display_name":"Yida Wang","orcid":"https://orcid.org/0000-0001-8165-840X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yida Wang","raw_affiliation_strings":["Amazon, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0000-0001-8165-840X","affiliations":[{"raw_affiliation_string":"Amazon, Santa Clara, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1707","last_page":"1721"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.26249998807907104,"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":0.26249998807907104,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.1972000002861023,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.08410000056028366,"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/language-model","display_name":"Language model","score":0.5324000120162964},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4912000000476837},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.3100000023841858},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.305400013923645},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2847000062465668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.704800009727478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5425999760627747},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5324000120162964},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4912000000476837},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4553000032901764},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.3100000023841858},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3012999892234802},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2653999924659729}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3767295.3769364","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769364","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 21st European Conference on Computer Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3767295.3769364","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769364","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 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W3131922516"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"large":[1],"language":[2],"models":[3],"rely":[4],"on":[5],"attention":[6,26],"mechanisms":[7],"that":[8,21],"attend":[9],"to":[10,34,45],"all":[11],"tokens":[12],"in":[13,17],"a":[14],"sequence,":[15],"resulting":[16],"quadratic":[18],"computational":[19],"complexity":[20,47],"limits":[22],"scalability.":[23],"While":[24],"sparse":[25,53],"reduces":[27],"compute":[28],"and":[29,51,55],"memory":[30],"requirements":[31],"by":[32],"attending":[33],"only":[35],"important":[36],"tokens,":[37],"implementing":[38],"these":[39],"techniques":[40],"presents":[41],"significant":[42],"challenges":[43],"due":[44],"the":[46],"of":[48],"combining":[49],"static":[50],"dynamic":[52],"patterns":[54],"optimizing":[56],"key-value":[57],"(KV)":[58],"cache":[59],"management.":[60]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-25T00:00:00"}