{"id":"https://openalex.org/W4411055208","doi":"https://doi.org/10.1109/access.2025.3576898","title":"BALI\u2014A Benchmark for Accelerated Language Model Inference","display_name":"BALI\u2014A Benchmark for Accelerated Language Model Inference","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411055208","doi":"https://doi.org/10.1109/access.2025.3576898"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3576898","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3576898","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3576898","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093073364","display_name":"Lena Jurkschat","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Lena Jurkschat","raw_affiliation_strings":["Center for Interdisciplinary Digital Sciences (CIDS), ScaDS.AI Dresden/Leipzig, Technische Universität Dresden, Dresden, Germany","Center for Interdisciplinary Digital Sciences (CIDS), Technische Universität Dresden, Germany"],"raw_orcid":"https://orcid.org/0009-0002-7332-5861","affiliations":[{"raw_affiliation_string":"Center for Interdisciplinary Digital Sciences (CIDS), ScaDS.AI Dresden/Leipzig, Technische Universität Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"Center for Interdisciplinary Digital Sciences (CIDS), Technische Universität Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092966862","display_name":"Preetam Gattogi","orcid":"https://orcid.org/0009-0001-4604-2009"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I4401726909","display_name":"Center for Scalable Data Analytics and Artificial Intelligence","ror":"https://ror.org/01t4ttr56","country_code":"DE","type":"education","lineage":["https://openalex.org/I4401726909","https://openalex.org/I78650965","https://openalex.org/I926574661"]},{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Preetam Gattogi","raw_affiliation_strings":["Center for Interdisciplinary Digital Sciences (CIDS), ScaDS.AI Dresden/Leipzig, Technische Universität Dresden, Dresden, Germany","Center for Scalable Data Anlytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig, Germany"],"raw_orcid":"https://orcid.org/0009-0001-4604-2009","affiliations":[{"raw_affiliation_string":"Center for Interdisciplinary Digital Sciences (CIDS), ScaDS.AI Dresden/Leipzig, Technische Universität Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"Center for Scalable Data Anlytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig, Germany","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I4401726909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102785999","display_name":"Sahar Vahdati","orcid":"https://orcid.org/0000-0002-7171-169X"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I4401726909","display_name":"Center for Scalable Data Analytics and Artificial Intelligence","ror":"https://ror.org/01t4ttr56","country_code":"DE","type":"education","lineage":["https://openalex.org/I4401726909","https://openalex.org/I78650965","https://openalex.org/I926574661"]},{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sahar Vahdati","raw_affiliation_strings":["Center for Interdisciplinary Digital Sciences (CIDS), ScaDS.AI Dresden/Leipzig, Technische Universität Dresden, Dresden, Germany","Center for Scalable Data Anlytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Interdisciplinary Digital Sciences (CIDS), ScaDS.AI Dresden/Leipzig, Technische Universität Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"Center for Scalable Data Anlytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig, Germany","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I4401726909"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067133778","display_name":"Jens Lehmann","orcid":"https://orcid.org/0000-0001-9108-4278"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I4401726909","display_name":"Center for Scalable Data Analytics and Artificial Intelligence","ror":"https://ror.org/01t4ttr56","country_code":"DE","type":"education","lineage":["https://openalex.org/I4401726909","https://openalex.org/I78650965","https://openalex.org/I926574661"]},{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens Lehmann","raw_affiliation_strings":["Center for Interdisciplinary Digital Sciences (CIDS), ScaDS.AI Dresden/Leipzig, Technische Universität Dresden, Dresden, Germany","Center for Scalable Data Anlytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Interdisciplinary Digital Sciences (CIDS), ScaDS.AI Dresden/Leipzig, Technische Universität Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"Center for Scalable Data Anlytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig, Germany","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I4401726909"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5093073364"],"corresponding_institution_ids":["https://openalex.org/I78650965"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05631419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"98976","last_page":"98989"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9588000178337097,"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/T10028","display_name":"Topic Modeling","score":0.9588000178337097,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9466999769210815,"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/computer-science","display_name":"Computer science","score":0.7754595279693604},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6965974569320679},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.640588641166687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4140649437904358},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4074450731277466},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.05968695878982544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7754595279693604},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6965974569320679},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.640588641166687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4140649437904358},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4074450731277466},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.05968695878982544},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3576898","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3576898","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1cae2238947b431cafffd9ed72168330","is_oa":true,"landing_page_url":"https://doaj.org/article/1cae2238947b431cafffd9ed72168330","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 98976-98989 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3576898","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3576898","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1710528165","display_name":null,"funder_award_id":"68GX21007J","funder_id":"https://openalex.org/F4303701741","funder_display_name":"Bundesministerium f\u00fcr Wirtschaft und Klimaschutz"},{"id":"https://openalex.org/G7668369193","display_name":null,"funder_award_id":"SCADS22B","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4303701741","display_name":"Bundesministerium f\u00fcr Wirtschaft und Klimaschutz","ror":"https://ror.org/02vgg2808"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320323644","display_name":"S\u00e4chsisches Staatsministerium f\u00fcr Wissenschaft und Kunst","ror":"https://ror.org/05wnef833"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W4387321091","https://openalex.org/W4390189088","https://openalex.org/W4399665841","https://openalex.org/W4402670850","https://openalex.org/W4404344662","https://openalex.org/W6767997687","https://openalex.org/W6768817161","https://openalex.org/W6769454693","https://openalex.org/W6811340617","https://openalex.org/W6846254642","https://openalex.org/W6850625674","https://openalex.org/W6852294668","https://openalex.org/W6854866820","https://openalex.org/W6855537017","https://openalex.org/W6855650390","https://openalex.org/W6856529530","https://openalex.org/W6856976311","https://openalex.org/W6857838382","https://openalex.org/W6857972656","https://openalex.org/W6858023062","https://openalex.org/W6861206314","https://openalex.org/W6862397664"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"rise":[1],"of":[2,78,87,132,149],"Large":[3],"Language":[4,116],"Models":[5],"(LLMs)":[6],"has":[7],"revolutionized":[8],"natural":[9],"language":[10],"processing,":[11],"enabling":[12],"advancements":[13],"across":[14,135,152],"diverse":[15],"applications,":[16],"including":[17,155],"chatbots,":[18],"live":[19],"translators,":[20],"content":[21],"generation,":[22],"virtual":[23],"assistants,":[24],"and":[25,48,61,105,124,145,159,202],"domain-specific":[26],"automation":[27],"tools.":[28],"These":[29,51,188],"applications":[30],"rely":[31],"on":[32],"real-time":[33,185],"or":[34,70,176],"near-real-time":[35],"responses":[36],"to":[37,55,75,91,120,128,143,168,209,223],"process":[38],"sequential":[39,156,175],"LLM":[40,133,150,186,211],"requests,":[41],"creating":[42],"a":[43,84,174,197,216],"critical":[44],"demand":[45],"for":[46,114,165,183,195],"efficient":[47],"accelerated":[49],"inference.":[50],"developments":[52],"have":[53],"led":[54],"numerous":[56],"frameworks":[57,89,151],"optimizing":[58],"inference":[59,102,213],"speed":[60],"resource":[62],"utilization.":[63],"However,":[64],"they":[65],"are":[66,71],"often":[67],"mutually":[68],"incomparable":[69],"inadequately":[72],"described":[73],"due":[74,90],"the":[76,92,130,147,192],"lack":[77,86],"standardized":[79,125],"benchmarks.":[80],"Consequently,":[81],"there":[82],"is":[83,180,208],"notable":[85],"comparison":[88],"vast":[93],"configuration":[94],"space,":[95],"bounded":[96],"factors":[97],"such":[98,196],"as":[99],"hardware":[100],"specifications,":[101],"framework":[103,198],"parameters,":[104],"dataset":[106],"variations.":[107],"We":[108,162],"propose":[109,140],"BALI,":[110,138],"an":[111,200,212],"open-source":[112],"Benchmark":[113],"Accelerated":[115],"Model":[117],"Inference,":[118],"aiming":[119],"provide":[121,210,224],"comprehensive":[122],"analysis":[123],"evaluation":[126],"metrics":[127],"enhance":[129],"comparability":[131],"performance":[134,226],"configurations.":[136],"With":[137],"we":[139],"substantial":[141],"measurements":[142],"evaluate":[144],"rank":[146],"efficiency":[148],"multiple":[153],"aspects,":[154],"decoding,":[157],"parallelization,":[158],"setup":[160],"efficiency.":[161],"show":[163],"results":[164],"mainly":[166],"small":[167],"medium-size":[169],"models":[170],"(1-30B":[171],"parameters)":[172],"in":[173],"non-batched":[177],"setup,":[178],"which":[179],"highly":[181],"relevant":[182],"various":[184],"applications.":[187],"observations":[189],"reveal":[190],"that":[191],"design":[193],"decisions":[194],"constitute":[199],"application-dependent":[201],"multidimensional":[203,221],"challenge.":[204],"Thus,":[205],"our":[206],"objective":[207],"benchmark":[214],"with":[215],"clearly":[217],"defined":[218],"evaluation,":[219],"incorporating":[220],"criteria":[222],"comparable":[225],"assessments.":[227]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-06-06T00:00:00"}