{"id":"https://openalex.org/W7163700631","doi":"https://doi.org/10.48550/arxiv.2606.06453","title":"Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents","display_name":"Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents","publication_year":2026,"publication_date":"2026-06-04","ids":{"openalex":"https://openalex.org/W7163700631","doi":"https://doi.org/10.48550/arxiv.2606.06453"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.06453","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06453","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.06453","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137948943","display_name":"Zhuoming Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhuoming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002304298","display_name":"Xinrui Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Xinrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137959860","display_name":"Qilong Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Qilong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137940358","display_name":"Ranajoy Sadhukhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sadhukhan, Ranajoy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137962152","display_name":"Yang Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137936791","display_name":"Michael Qizhe Shieh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shieh, Michael Qizhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137964247","display_name":"Zhihao Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Zhihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137959552","display_name":"Beidi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Beidi","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":false,"cited_by_count":0,"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":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.353300005197525,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.353300005197525,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.15530000627040863,"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/T14347","display_name":"Big Data and Digital Economy","score":0.06599999964237213,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/abstraction","display_name":"Abstraction","score":0.6425999999046326},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.641700029373169},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.42179998755455017},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.413100004196167},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.3206999897956848}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401999831199646},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6425999999046326},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.641700029373169},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.42179998755455017},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38929998874664307},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2856999933719635},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.2655999958515167}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.06453","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06453","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.06453","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06453","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Sparse":[0],"attention":[1,24,42,71,93,117,141,149],"is":[2],"becoming":[3],"increasingly":[4],"important":[5],"for":[6,64],"serving":[7,82],"large":[8,155],"language":[9,58],"models":[10,156],"(LLMs)":[11],"as":[12],"generation":[13],"lengths":[14],"continue":[15],"to":[16,124,135,150,161,166],"grow.":[17],"However,":[18],"deploying":[19],"and":[20,35,89,113,127,153,174],"evaluating":[21],"new":[22],"sparse":[23,41,70,92,116,148],"algorithms":[25],"at":[26],"scale":[27],"remains":[28],"highly":[29],"engineering-intensive,":[30],"slowing":[31],"both":[32],"human":[33],"researchers":[34],"AI":[36,120],"agents":[37,121],"in":[38],"exploring":[39],"the":[40,111,131,171,177],"design.":[43],"To":[44],"address":[45],"this":[46],"challenge,":[47],"we":[48],"present":[49],"Vortex,":[50],"a":[51,55,60,66,106],"system":[52],"that":[53,157],"combines":[54],"Python-embedded":[56],"frontend":[57],"atop":[59],"page-centric":[61],"tensor":[62],"abstraction":[63],"expressing":[65],"broad":[67],"range":[68],"of":[69,91,115],"algorithms,":[72,94,130],"with":[73],"an":[74],"efficient":[75],"backend":[76],"tightly":[77],"integrated":[78],"into":[79,101],"modern":[80],"LLM":[81],"stacks.":[83],"Vortex":[84,108,123,146],"enables":[85],"rapid":[86],"prototyping,":[87],"deployment,":[88],"evaluation":[90],"effectively":[95],"translating":[96],"their":[97],"theoretical":[98],"efficiency":[99],"gains":[100],"real-world":[102],"throughput":[103,138,169],"improvements.":[104],"As":[105],"result,":[107],"substantially":[109],"accelerates":[110],"design":[112],"iteration":[114],"algorithms.":[118],"First,":[119],"use":[122],"automatically":[125],"generate":[126],"refine":[128],"diverse":[129],"best":[132],"reaching":[133,164],"up":[134,165],"$3.46\\times$":[136],"higher":[137,168],"than":[139],"full":[140],"while":[142],"preserving":[143],"accuracy.":[144],"Second,":[145],"extends":[147],"emerging":[151],"architectures":[152],"very":[154],"are":[158],"otherwise":[159],"hard":[160],"experiment":[162],"with,":[163],"$4.7\\times$":[167],"on":[170,176,180],"MLA-based":[172],"GLM-4.7-Flash":[173],"$1.37\\times$":[175],"229B-parameter":[178],"MiniMax-M2.7":[179],"NVIDIA":[181],"B200":[182],"GPUs.":[183]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-06T00:00:00"}