{"id":"https://openalex.org/W7106322335","doi":"https://doi.org/10.5281/zenodo.17673796","title":"Artifact for the PPoPP '26 paper: \"FlashAttention-T: Towards Fully Tensorized Attention by Exploiting Tensor\u2013Vector Parallelism.\"","display_name":"Artifact for the PPoPP '26 paper: \"FlashAttention-T: Towards Fully Tensorized Attention by Exploiting Tensor\u2013Vector Parallelism.\"","publication_year":2025,"publication_date":"2025-11-22","ids":{"openalex":"https://openalex.org/W7106322335","doi":"https://doi.org/10.5281/zenodo.17673796"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.17673796","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17673796","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},"type":"software","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17673796","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xu, Jianxing","orcid":"https://orcid.org/0000-0002-0373-411X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Jianxing","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":"https://orcid.org/0000-0002-0373-411X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wen, Yuanbo","orcid":"https://orcid.org/0000-0002-7775-2724"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen, Yuanbo","raw_affiliation_strings":["Institute of Computing Technology"],"raw_orcid":"https://orcid.org/0000-0002-7775-2724","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bi, Jun","orcid":"https://orcid.org/0000-0001-9956-7039"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bi, Jun","raw_affiliation_strings":["Institute of Computing Technology"],"raw_orcid":"https://orcid.org/0000-0001-9956-7039","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xu, Ruibai","orcid":"https://orcid.org/0009-0003-1830-4483"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Ruibai","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":"https://orcid.org/0009-0003-1830-4483","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.9196000099182129},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.8263000249862671},{"id":"https://openalex.org/keywords/idle","display_name":"Idle","score":0.6607000231742859},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5184000134468079},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5121999979019165},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.47099998593330383}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.9196000099182129},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.8263000249862671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7603999972343445},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.6607000231742859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5329999923706055},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5121999979019165},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.47099998593330383},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.39160001277923584},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17673796","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17673796","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Software"}],"best_oa_location":{"id":"doi:10.5281/zenodo.17673796","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17673796","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"is":[1,20,40],"the":[2,6,77,80,91,106,109,120],"artifact":[3,110,121],"package":[4,111],"for":[5,65,114,125],"PPoPP":[7],"'26":[8],"paper:":[9],"\u201cFlashAttention-T:":[10],"Towards":[11],"Fully":[12],"Tensorized":[13],"Attention":[14],"by":[15],"Exploiting":[16],"Tensor\u2013Vector":[17],"Parallelism.\u201d":[18],"FlashAttention-T":[19],"a":[21,69,115],"prototype":[22],"fused-attention":[23],"implementation":[24],"built":[25],"on":[26,100],"FlashAttention-2":[27],"and":[28,53,85,97,122],"FlashAttention-3":[29],"that":[30,74,89],"advances":[31],"toward":[32],"fully":[33],"tensorized":[34,70],"fused":[35],"attention.":[36],"The":[37],"key":[38],"technique":[39],"offloading":[41],"critical":[42],"softmax":[43,67,72,93],"primitives":[44],"to":[45,60,76,105],"otherwise":[46],"idle":[47],"tensor":[48,62,82,96],"units,":[49],"maximizing":[50],"hardware":[51],"utilization":[52],"throughput.":[54],"In":[55],"FlashAttention-T,":[56],"we":[57],"implement":[58],"methods":[59],"repurpose":[61],"MMA":[63,83],"instructions":[64],"executing":[66],"primitives,":[68],"online":[71,92],"algorithm":[73],"adheres":[75],"constraints":[78],"of":[79,119],"repurposed":[81],"instructions,":[84],"architecture-aware":[86],"scheduling":[87],"techniques":[88],"parallelize":[90],"computation":[94],"across":[95],"vector":[98],"units":[99],"NVIDIA":[101],"GPUs.":[102],"Please":[103],"refer":[104],"README.md":[107],"inside":[108],"(ZIP":[112],"file)":[113],"more":[116],"detailed":[117],"overview":[118],"step-by-step":[123],"guides":[124],"evaluating":[126],"it.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-11-23T00:00:00"}