{"id":"https://openalex.org/W7204453278","doi":"https://doi.org/10.21105/joss.10314","title":"Inference Perf: A Benchmarking Tool for GenAI Inference","display_name":"Inference Perf: A Benchmarking Tool for GenAI Inference","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204453278","doi":"https://doi.org/10.21105/joss.10314"},"language":"en","primary_location":{"id":"doi:10.21105/joss.10314","doi":"https://doi.org/10.21105/joss.10314","is_oa":true,"landing_page_url":"https://doi.org/10.21105/joss.10314","pdf_url":"https://joss.theoj.org/papers/10.21105/joss.10314.pdf","source":{"id":"https://openalex.org/S4210214273","display_name":"The Journal of Open Source Software","issn_l":"2475-9066","issn":["2475-9066"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315853","host_organization_name":"Open Journals","host_organization_lineage":["https://openalex.org/P4310315853"],"host_organization_lineage_names":["Open Journals"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Open Source Software","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://joss.theoj.org/papers/10.21105/joss.10314.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103419947","display_name":"Ashok Chandrasekar","orcid":"https://orcid.org/0009-0009-3481-9173","observed_orcids":["https://orcid.org/0009-0009-3481-9173"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashok Chandrasekar","raw_affiliation_strings":["Google, USA"],"raw_orcid":"https://orcid.org/0009-0009-3481-9173","affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146454981","display_name":"Sachin Mathew Varghese","orcid":"https://orcid.org/0009-0007-5015-5173","observed_orcids":["https://orcid.org/0009-0007-5015-5173"]},"institutions":[{"id":"https://openalex.org/I1305444813","display_name":"Capital One (United States)","ror":"https://ror.org/00svp7168","country_code":"US","type":"company","lineage":["https://openalex.org/I1305444813"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sachin Varghese","raw_affiliation_strings":["Capital One, USA"],"raw_orcid":"https://orcid.org/0009-0007-5015-5173","affiliations":[{"raw_affiliation_string":"Capital One, USA","institution_ids":["https://openalex.org/I1305444813"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146520506","display_name":"Jason Kramberger","orcid":"https://orcid.org/0009-0006-8517-7973","observed_orcids":["https://orcid.org/0009-0006-8517-7973"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Kramberger","raw_affiliation_strings":["Google, USA"],"raw_orcid":"https://orcid.org/0009-0006-8517-7973","affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146512626","display_name":"Brendan Slabe","orcid":"https://orcid.org/0009-0005-1730-753X","observed_orcids":["https://orcid.org/0009-0005-1730-753X"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brendan Slabe","raw_affiliation_strings":["Google, USA"],"raw_orcid":"https://orcid.org/0009-0005-1730-753X","affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337643","display_name":"Chen Wang","orcid":"https://orcid.org/0000-0003-0204-2362","observed_orcids":["https://orcid.org/0000-0003-0204-2362"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Wang","raw_affiliation_strings":["IBM Research, USA"],"raw_orcid":"https://orcid.org/0000-0003-0204-2362","affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101981296","display_name":"Yuan Tang","orcid":"https://orcid.org/0000-0001-5243-233X","observed_orcids":["https://orcid.org/0000-0001-5243-233X"]},"institutions":[{"id":"https://openalex.org/I1328219102","display_name":"Red Hat (United States)","ror":"https://ror.org/03ncs3316","country_code":"US","type":"company","lineage":["https://openalex.org/I1328219102"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Tang","raw_affiliation_strings":["Red Hat, USA"],"raw_orcid":"https://orcid.org/0000-0001-5243-233X","affiliations":[{"raw_affiliation_string":"Red Hat, USA","institution_ids":["https://openalex.org/I1328219102"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57005863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"124","first_page":"10314","last_page":"10314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.8798999786376953,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.8798999786376953,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.08250000327825546,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.012299999594688416,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/kubernetes","display_name":"Kubernetes","score":0.5199999809265137}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8105000257492065},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8008999824523926},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178999781608582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5637000203132629},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4625000059604645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41179999709129333},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.2583000063896179},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2272000014781952}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21105/joss.10314","doi":"https://doi.org/10.21105/joss.10314","is_oa":true,"landing_page_url":"https://doi.org/10.21105/joss.10314","pdf_url":"https://joss.theoj.org/papers/10.21105/joss.10314.pdf","source":{"id":"https://openalex.org/S4210214273","display_name":"The Journal of Open Source Software","issn_l":"2475-9066","issn":["2475-9066"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315853","host_organization_name":"Open Journals","host_organization_lineage":["https://openalex.org/P4310315853"],"host_organization_lineage_names":["Open Journals"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Open Source Software","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.21105/joss.10314","doi":"https://doi.org/10.21105/joss.10314","is_oa":true,"landing_page_url":"https://doi.org/10.21105/joss.10314","pdf_url":"https://joss.theoj.org/papers/10.21105/joss.10314.pdf","source":{"id":"https://openalex.org/S4210214273","display_name":"The Journal of Open Source Software","issn_l":"2475-9066","issn":["2475-9066"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315853","host_organization_name":"Open Journals","host_organization_lineage":["https://openalex.org/P4310315853"],"host_organization_lineage_names":["Open Journals"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Open Source Software","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204453278.pdf","grobid_xml":"https://content.openalex.org/works/W7204453278.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W3043571714","https://openalex.org/W4387321091","https://openalex.org/W4415797413"],"related_works":["https://openalex.org/W7155394969","https://openalex.org/W3188783383","https://openalex.org/W4206166505","https://openalex.org/W4415088363","https://openalex.org/W7170286594","https://openalex.org/W7160043388","https://openalex.org/W6931540726","https://openalex.org/W7214102074","https://openalex.org/W7214714701","https://openalex.org/W7160109547"],"abstract_inverted_index":{"Inference":[0],"Perf":[1],"is":[2,21],"a":[3,41],"generative":[4],"AI":[5],"(GenAI)":[6],"inference":[7,19,45,69],"performance":[8,17,70],"benchmarking":[9,13,46],"tool":[10],"aimed":[11],"at":[12],"and":[14,35,47,60,65,74],"analyzing":[15],"the":[16,44,52,72],"of":[18,43],"deployments.It":[20],"designed":[22],"to":[23,62],"be":[24],"model":[25,33,75],"server-agnostic,":[26],"allowing":[27],"for":[28,67],"apples-to-apples":[29],"comparisons":[30],"across":[31,71],"different":[32],"servers":[34],"serving":[36],"stacks.It":[37],"was":[38],"created":[39],"as":[40],"part":[42],"metrics":[48,66],"standardization":[49],"effort":[50],"in":[51],"Kubernetes":[53,73],"wg-serving":[54],"working":[55],"group":[56],"(Kubernetes":[57],"Authors,":[58],"2024),":[59],"seeks":[61],"standardize":[63],"tooling":[64],"measuring":[68],"server":[76],"communities.":[77]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-28T00:00:00"}
