{"id":"https://openalex.org/W4386768680","doi":"https://doi.org/10.14778/3611540.3611564","title":"Angel-PTM: A Scalable and Economical Large-Scale Pre-Training System in Tencent","display_name":"Angel-PTM: A Scalable and Economical Large-Scale Pre-Training System in Tencent","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4386768680","doi":"https://doi.org/10.14778/3611540.3611564"},"language":"en","primary_location":{"id":"doi:10.14778/3611540.3611564","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3611540.3611564","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059601307","display_name":"Xiaonan Nie","orcid":"https://orcid.org/0000-0001-6766-757X"},"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":"Xiaonan Nie","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330635","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0003-3056-7713"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Tencent Inc"],"affiliations":[{"raw_affiliation_string":"Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039254679","display_name":"Fangcheng Fu","orcid":"https://orcid.org/0000-0003-1658-0380"},"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":"Fangcheng Fu","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025328651","display_name":"Jinbao Xue","orcid":"https://orcid.org/0009-0003-4087-9873"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinbao Xue","raw_affiliation_strings":["Tencent Inc"],"affiliations":[{"raw_affiliation_string":"Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112314791","display_name":"Dian Jiao","orcid":"https://orcid.org/0000-0002-1435-2061"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dian Jiao","raw_affiliation_strings":["Tencent Inc"],"affiliations":[{"raw_affiliation_string":"Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015552951","display_name":"Xupeng Miao","orcid":"https://orcid.org/0000-0002-9371-8358"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xupeng Miao","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077922409","display_name":"Yangyu Tao","orcid":"https://orcid.org/0009-0003-0536-4321"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangyu Tao","raw_affiliation_strings":["Tencent Inc"],"affiliations":[{"raw_affiliation_string":"Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062357883","display_name":"Bin Cui","orcid":"https://orcid.org/0000-0003-1681-4677"},"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":"Bin Cui","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5059601307"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.2056,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81549043,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"16","issue":"12","first_page":"3781","last_page":"3794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9980999827384949,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9980999827384949,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.996999979019165,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9955000281333923,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8440650105476379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8345412611961365},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.613177478313446},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.490268737077713},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48489052057266235},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4554166793823242},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4431428909301758},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1741822063922882},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07894465327262878},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07454648613929749}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8440650105476379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8345412611961365},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.613177478313446},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.490268737077713},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48489052057266235},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4554166793823242},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4431428909301758},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1741822063922882},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07894465327262878},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07454648613929749},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3611540.3611564","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3611540.3611564","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2060393849","https://openalex.org/W2151822116","https://openalex.org/W2153190325","https://openalex.org/W2194775991","https://openalex.org/W2764065518","https://openalex.org/W2799200478","https://openalex.org/W2892009249","https://openalex.org/W2981852735","https://openalex.org/W2981857663","https://openalex.org/W3119866685","https://openalex.org/W3129831491","https://openalex.org/W3138516171","https://openalex.org/W3155426438","https://openalex.org/W3158196591","https://openalex.org/W3177263144","https://openalex.org/W3189259198","https://openalex.org/W3189646782","https://openalex.org/W3204998121","https://openalex.org/W3205803342","https://openalex.org/W4226328099","https://openalex.org/W4226479682","https://openalex.org/W4283073926","https://openalex.org/W4283516491","https://openalex.org/W4287121196","https://openalex.org/W4287391717","https://openalex.org/W4288089799","https://openalex.org/W4289446312","https://openalex.org/W4289533987","https://openalex.org/W4301361180","https://openalex.org/W4307994214","https://openalex.org/W4311209912","https://openalex.org/W4312933868","https://openalex.org/W4364382874","https://openalex.org/W6796487566"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W1982914007","https://openalex.org/W2159583675","https://openalex.org/W2981757109","https://openalex.org/W1852113167","https://openalex.org/W1493858311","https://openalex.org/W1824242903","https://openalex.org/W2155470929","https://openalex.org/W2394465510","https://openalex.org/W2111125783"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2,28],"witnessed":[3],"the":[4,34,78,110],"unprecedented":[5],"achievements":[6],"of":[7,36,70,128,140,152],"large-scale":[8,61],"pre-trained":[9,37],"models,":[10],"especially":[11],"Transformer":[12,55],"models.":[13,38,56],"Many":[14],"products":[15],"and":[16,25,53,81,91,102,147],"services":[17],"in":[18,31,126,138],"Tencent":[19,26],"Inc.,":[20],"such":[21],"as":[22,132,134],"WeChat,":[23],"QQ,":[24],"Advertisement,":[27],"been":[29],"opted":[30],"to":[32,108,124,136],"gain":[33],"power":[35],"In":[39],"this":[40],"work,":[41],"we":[42],"present":[43],"Angel-PTM,":[44],"a":[45,73,82,104],"productive":[46],"deep":[47],"learning":[48],"system":[49],"designed":[50],"for":[51],"pre-training":[52],"fine-tuning":[54],"Angel-PTM":[57,71,94,118],"can":[58],"train":[59],"extremely":[60],"models":[62,149],"with":[63,99],"hierarchical":[64],"memory":[65,75],"efficiently.":[66],"The":[67],"key":[68],"designs":[69],"are":[72],"fine-grained":[74],"management":[76],"via":[77],"Page":[79],"abstraction":[80],"unified":[83],"scheduling":[84],"method":[85],"that":[86,117],"coordinates":[87],"computations,":[88],"data":[89],"movements,":[90],"communications.":[92],"Furthermore,":[93],"supports":[95],"extreme":[96],"model":[97,130],"scaling":[98],"SSD":[100,111],"storage":[101],"implements":[103],"lock-free":[105],"updating":[106],"mechanism":[107],"address":[109],"I/O":[112],"bottlenecks.":[113],"Experimental":[114],"results":[115],"demonstrate":[116],"outperforms":[119],"existing":[120],"systems":[121],"by":[122],"up":[123,135],"114.8%":[125],"terms":[127,139],"maximum":[129],"scale":[131],"well":[133],"88.9%":[137],"training":[141],"throughput.":[142],"Additionally,":[143],"experiments":[144],"on":[145],"GPT3-175B":[146],"T5-MoE-1.2T":[148],"utilizing":[150],"hundreds":[151],"GPUs":[153],"verify":[154],"our":[155],"strong":[156],"scalability.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
