{"id":"https://openalex.org/W4416004263","doi":"https://doi.org/10.1145/3731599.3767706","title":"MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models","display_name":"MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004263","doi":"https://doi.org/10.1145/3731599.3767706"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767706","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767706","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731599.3767706","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015607198","display_name":"Krishna Teja Chitty-Venkata","orcid":"https://orcid.org/0000-0002-3027-1915"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Krishna Teja Chitty-Venkata","raw_affiliation_strings":["Argonne National Laboratory (ANL), Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory (ANL), Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105330155","display_name":"Sylvia Howland","orcid":"https://orcid.org/0009-0009-7846-751X"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sylvia Howland","raw_affiliation_strings":["Cerebras, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Cerebras, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092938696","display_name":"Golara Ahmadi Azar","orcid":"https://orcid.org/0009-0000-2016-2822"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Golara Azar","raw_affiliation_strings":["Cerebras, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Cerebras, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057449462","display_name":"Daria Soboleva","orcid":"https://orcid.org/0009-0003-2654-3767"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daria Soboleva","raw_affiliation_strings":["Cerebras, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Cerebras, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099338040","display_name":"Natalia Vassilieva","orcid":"https://orcid.org/0009-0003-1038-1572"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Natalia Vassilieva","raw_affiliation_strings":["Cerebras, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Cerebras, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039783562","display_name":"Siddhisanket Raskar","orcid":"https://orcid.org/0000-0002-4832-0834"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhisanket Raskar","raw_affiliation_strings":["Pacific Northwest National Laboratory (PNNL), Providence, RI, USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory (PNNL), Providence, RI, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014448094","display_name":"Murali Emani","orcid":"https://orcid.org/0000-0002-6279-0007"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murali Emani","raw_affiliation_strings":["Argonne National Laboratory (ANL), Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory (ANL), Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075500139","display_name":"Venkatram Vishwanath","orcid":"https://orcid.org/0000-0001-7248-6116"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkatram Vishwanath","raw_affiliation_strings":["Argonne National Laboratory (ANL), Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory (ANL), Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5015607198"],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33542198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1502","last_page":"1511"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.36959999799728394,"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":0.36959999799728394,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.13459999859333038,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1054999977350235,"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/software-deployment","display_name":"Software deployment","score":0.5558000206947327},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5338000059127808},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4611000120639801},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3734000027179718},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.34769999980926514},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.3427000045776367},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.3343999981880188},{"id":"https://openalex.org/keywords/toolbox","display_name":"Toolbox","score":0.31940001249313354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829999923706055},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5558000206947327},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5338000059127808},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5317000150680542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5134999752044678},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767706","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767706","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731599.3767706","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767706","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2307512708","https://openalex.org/W2890894339","https://openalex.org/W2923014074","https://openalex.org/W2946609015","https://openalex.org/W2979382951","https://openalex.org/W3120043490","https://openalex.org/W3137147200","https://openalex.org/W3213061620","https://openalex.org/W4213213306","https://openalex.org/W4220967350","https://openalex.org/W4318603275","https://openalex.org/W4324292875","https://openalex.org/W4376652719","https://openalex.org/W4380885974","https://openalex.org/W4387321091","https://openalex.org/W4401017948","https://openalex.org/W4402716477","https://openalex.org/W4403791888","https://openalex.org/W4404792840","https://openalex.org/W4406164090","https://openalex.org/W6893007900"],"related_works":[],"abstract_inverted_index":{"Mixture":[0],"of":[1,9,54,59,82,97,148],"Experts":[2],"(MoE)":[3],"models":[4],"have":[5],"enabled":[6],"the":[7,40,52,80,127,145],"scaling":[8],"Large":[10],"Language":[11,16],"Models":[12,17],"(LLMs)":[13],"and":[14,39,49,87,95,118,131,141],"Vision":[15],"(VLMs)":[18],"by":[19],"achieving":[20],"massive":[21],"parameter":[22],"counts":[23],"while":[24],"maintaining":[25],"computational":[26,43],"efficiency.":[27],"However,":[28],"MoEs":[29,125],"introduce":[30],"several":[31,103],"inference-time":[32],"challenges,":[33],"including":[34,110],"load":[35],"imbalance":[36],"across":[37,75,139],"experts":[38,98],"additional":[41],"routing":[42],"overhead.":[44],"To":[45],"address":[46],"these":[47],"challenges":[48],"fully":[50],"harness":[51],"benefits":[53],"MoE,":[55],"a":[56,68],"systematic":[57],"evaluation":[58,123],"hardware":[60],"acceleration":[61],"techniques":[62,105],"is":[63],"essential.":[64],"We":[65,78,101],"present":[66],"MoE-Inference-Bench,":[67],"comprehensive":[69],"study":[70],"to":[71],"evaluate":[72,102],"MoE":[73,89,113],"performance":[74,137],"diverse":[76],"scenarios.":[77],"analyze":[79],"impact":[81],"batch":[83],"size,":[84],"sequence":[85],"length,":[86],"critical":[88],"hyperparameters":[90],"such":[91],"as":[92],"FFN":[93],"dimensions":[94],"number":[96],"on":[99,106],"throughput.":[100],"optimization":[104],"Nvidia":[107],"H100":[108],"GPUs,":[109],"pruning,":[111],"Fused":[112],"operations,":[114],"speculative":[115],"decoding,":[116],"quantization,":[117],"various":[119],"parallelization":[120],"strategies.":[121],"Our":[122],"includes":[124],"from":[126],"Mixtral,":[128],"DeepSeek,":[129],"OLMoE":[130],"Qwen":[132],"families.":[133],"The":[134],"results":[135],"reveal":[136],"differences":[138],"configurations":[140],"provide":[142],"insights":[143],"for":[144],"efficient":[146],"deployment":[147],"MoEs.":[149]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-07T00:00:00"}