{"id":"https://openalex.org/W4415901343","doi":"https://doi.org/10.1145/3767295.3769325","title":"MegaScale-MoE: Large-Scale Communication-Efficient Training of Mixture-of-Experts Models in Production","display_name":"MegaScale-MoE: Large-Scale Communication-Efficient Training of Mixture-of-Experts Models in Production","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W4415901343","doi":"https://doi.org/10.1145/3767295.3769325"},"language":"en","primary_location":{"id":"doi:10.1145/3767295.3769325","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769325","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767295.3769325","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074344378","display_name":"Chao Jin","orcid":"https://orcid.org/0000-0001-6590-333X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chao Jin","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-1355-4995","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008448494","display_name":"Ziheng Jiang","orcid":"https://orcid.org/0000-0002-6392-6615"},"institutions":[{"id":"https://openalex.org/I1316868585","display_name":"Fidal","ror":"https://ror.org/04nwdyy60","country_code":"FR","type":"other","lineage":["https://openalex.org/I1316868585"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ziheng Jiang","raw_affiliation_strings":["ByteDance Seed, Seattle, USA"],"raw_orcid":"https://orcid.org/0009-0001-7732-4391","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Seattle, USA","institution_ids":["https://openalex.org/I1316868585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027997150","display_name":"Zhihao Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I1316868585","display_name":"Fidal","ror":"https://ror.org/04nwdyy60","country_code":"FR","type":"other","lineage":["https://openalex.org/I1316868585"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Zhihao Bai","raw_affiliation_strings":["ByteDance Seed, Seattle, USA"],"raw_orcid":"https://orcid.org/0000-0002-2223-1921","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Seattle, USA","institution_ids":["https://openalex.org/I1316868585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108708806","display_name":"Zheng Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I1316868585","display_name":"Fidal","ror":"https://ror.org/04nwdyy60","country_code":"FR","type":"other","lineage":["https://openalex.org/I1316868585"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Zheng Zhong","raw_affiliation_strings":["ByteDance Seed, Seattle, USA"],"raw_orcid":"https://orcid.org/0009-0000-2066-1779","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Seattle, USA","institution_ids":["https://openalex.org/I1316868585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505957","display_name":"Juncai Liu","orcid":"https://orcid.org/0000-0003-1448-7553"},"institutions":[{"id":"https://openalex.org/I4210128111","display_name":"Clover Seed (China)","ror":"https://ror.org/037jwt041","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128111"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juncai Liu","raw_affiliation_strings":["ByteDance Seed, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5783-731X","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Shanghai, China","institution_ids":["https://openalex.org/I4210128111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100745285","display_name":"Xiang Li","orcid":"https://orcid.org/0009-0009-0556-5290"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["ByteDance Seed, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-8712-9692","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018118687","display_name":"Ningxin Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128111","display_name":"Clover Seed (China)","ror":"https://ror.org/037jwt041","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128111"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningxin Zheng","raw_affiliation_strings":["ByteDance Seed, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-1147-6984","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Shanghai, China","institution_ids":["https://openalex.org/I4210128111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101507173","display_name":"Xi Wang","orcid":"https://orcid.org/0000-0002-4186-4935"},"institutions":[{"id":"https://openalex.org/I4210128111","display_name":"Clover Seed (China)","ror":"https://ror.org/037jwt041","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128111"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Wang","raw_affiliation_strings":["ByteDance Seed, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-4036-2175","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Shanghai, China","institution_ids":["https://openalex.org/I4210128111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101604495","display_name":"Cong Xie","orcid":"https://orcid.org/0009-0002-7979-3965"},"institutions":[{"id":"https://openalex.org/I1316868585","display_name":"Fidal","ror":"https://ror.org/04nwdyy60","country_code":"FR","type":"other","lineage":["https://openalex.org/I1316868585"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cong Xie","raw_affiliation_strings":["ByteDance Seed, Seattle, USA"],"raw_orcid":"https://orcid.org/0000-0002-5682-0230","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Seattle, USA","institution_ids":["https://openalex.org/I1316868585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102097114","display_name":"Qi Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Huang","raw_affiliation_strings":["ByteDance Seed, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-2143-7494","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925081","display_name":"Wen Heng","orcid":"https://orcid.org/0000-0002-8780-6693"},"institutions":[{"id":"https://openalex.org/I4210128111","display_name":"Clover Seed (China)","ror":"https://ror.org/037jwt041","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128111"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Heng","raw_affiliation_strings":["ByteDance Seed, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-7862-8059","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Shanghai, China","institution_ids":["https://openalex.org/I4210128111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057384195","display_name":"Yiyuan Ma","orcid":"https://orcid.org/0009-0000-0693-577X"},"institutions":[{"id":"https://openalex.org/I3130757197","display_name":"Distance State University","ror":"https://ror.org/0529rbt18","country_code":"CR","type":"education","lineage":["https://openalex.org/I3130757197"]}],"countries":["CR"],"is_corresponding":false,"raw_author_name":"Yiyuan Ma","raw_affiliation_strings":["ByteDance Seed, San Jose, USA"],"raw_orcid":"https://orcid.org/0009-0002-1070-7256","affiliations":[{"raw_affiliation_string":"ByteDance Seed, San Jose, USA","institution_ids":["https://openalex.org/I3130757197"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101002780","display_name":"Wenlei Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I1316868585","display_name":"Fidal","ror":"https://ror.org/04nwdyy60","country_code":"FR","type":"other","lineage":["https://openalex.org/I1316868585"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Wenlei Bao","raw_affiliation_strings":["ByteDance Seed, Seattle, USA"],"raw_orcid":"https://orcid.org/0009-0009-0826-8283","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Seattle, USA","institution_ids":["https://openalex.org/I1316868585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044708952","display_name":"Size Zheng","orcid":"https://orcid.org/0000-0002-6006-6277"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Size Zheng","raw_affiliation_strings":["ByteDance Seed, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9471-1780","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013856812","display_name":"Yanghua Peng","orcid":"https://orcid.org/0000-0003-3989-4358"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuegui Zheng","raw_affiliation_strings":["ByteDance Seed, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-4635-7309","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084047386","display_name":"Haibin Lin","orcid":"https://orcid.org/0000-0003-4879-5335"},"institutions":[{"id":"https://openalex.org/I1316868585","display_name":"Fidal","ror":"https://ror.org/04nwdyy60","country_code":"FR","type":"other","lineage":["https://openalex.org/I1316868585"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yanghua Peng","raw_affiliation_strings":["ByteDance Seed, Seattle, USA"],"raw_orcid":"https://orcid.org/0000-0003-3989-4358","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Seattle, USA","institution_ids":["https://openalex.org/I1316868585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052249316","display_name":"Xuanzhe Liu","orcid":"https://orcid.org/0000-0002-7908-8484"},"institutions":[{"id":"https://openalex.org/I1316868585","display_name":"Fidal","ror":"https://ror.org/04nwdyy60","country_code":"FR","type":"other","lineage":["https://openalex.org/I1316868585"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Haibin Lin","raw_affiliation_strings":["ByteDance Seed, Seattle, USA"],"raw_orcid":"https://orcid.org/0000-0003-4879-5335","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Seattle, USA","institution_ids":["https://openalex.org/I1316868585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101882004","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0001-8741-5847"},"institutions":[{"id":"https://openalex.org/I1316868585","display_name":"Fidal","ror":"https://ror.org/04nwdyy60","country_code":"FR","type":"other","lineage":["https://openalex.org/I1316868585"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","FR"],"is_corresponding":false,"raw_author_name":"Xuanzhe Liu","raw_affiliation_strings":["ByteDance Seed, Seattle, USA","School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7908-8484","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Seattle, USA","institution_ids":["https://openalex.org/I1316868585"]},{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113343221","display_name":"Xin Liu","orcid":"https://orcid.org/0009-0000-8346-3323"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8741-5847","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113343221","display_name":"Xin Liu","orcid":"https://orcid.org/0009-0000-8346-3323"},"institutions":[{"id":"https://openalex.org/I1316868585","display_name":"Fidal","ror":"https://ror.org/04nwdyy60","country_code":"FR","type":"other","lineage":["https://openalex.org/I1316868585"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","FR"],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["ByteDance Seed, Seattle, USA","School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-8346-3323","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Seattle, USA","institution_ids":["https://openalex.org/I1316868585"]},{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":20,"corresponding_author_ids":["https://openalex.org/A5074344378"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00565746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"366","last_page":"382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09619999676942825,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09619999676942825,"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":0.0957999974489212,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.09139999747276306,"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/training","display_name":"Training (meteorology)","score":0.7882999777793884},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5835000276565552},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.5594000220298767},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5570999979972839},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.43540000915527344},{"id":"https://openalex.org/keywords/communications-system","display_name":"Communications system","score":0.3840000033378601},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.3813000023365021}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7882999777793884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6536999940872192},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5835000276565552},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.5594000220298767},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5570999979972839},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C2776857766","wikidata":"https://www.wikidata.org/wiki/Q7832987","display_name":"Training system","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C158156997","wikidata":"https://www.wikidata.org/wiki/Q1416645","display_name":"Models of communication","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C2992770021","wikidata":"https://www.wikidata.org/wiki/Q7247850","display_name":"Production model","level":3,"score":0.2784999907016754},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2718999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3767295.3769325","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769325","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European Conference on Computer Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.11432","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11432","pdf_url":"https://arxiv.org/pdf/2505.11432","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.11432","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.11432","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3767295.3769325","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769325","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"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":{"We":[0],"present":[1],"MegaScale-MoE,":[2],"a":[3,19,41],"production":[4],"system":[5],"tailored":[6],"for":[7],"the":[8,48,55],"efficient":[9],"training":[10,38,44],"of":[11,51,58],"large-scale":[12],"mixture-of-experts":[13],"(MoE)":[14],"models.":[15],"MoE":[16,37,52],"emerges":[17],"as":[18],"promising":[20],"architecture":[21],"to":[22,28],"scale":[23,50],"large":[24],"language":[25],"models":[26,53],"(LLMs)":[27],"unprecedented":[29],"sizes,":[30],"thereby":[31],"enhancing":[32],"model":[33],"performance.":[34],"However,":[35],"existing":[36],"systems":[39],"experience":[40],"degradation":[42],"in":[43],"efficiency,":[45],"exacerbated":[46],"by":[47],"escalating":[49],"and":[54],"continuous":[56],"evolution":[57],"hardware.":[59]},"counts_by_year":[],"updated_date":"2026-04-26T06:01:38.667478","created_date":"2025-10-10T00:00:00"}