{"id":"https://openalex.org/W7168018002","doi":"https://doi.org/10.1145/3806645.3807815","title":"ResiHP: Taming LLM Training Failures with Dynamic Hybrid Parallelism","display_name":"ResiHP: Taming LLM Training Failures with Dynamic Hybrid Parallelism","publication_year":2026,"publication_date":"2026-07-11","ids":{"openalex":"https://openalex.org/W7168018002","doi":"https://doi.org/10.1145/3806645.3807815"},"language":null,"primary_location":{"id":"doi:10.1145/3806645.3807815","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806645.3807815","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 35th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3806645.3807815","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140479523","display_name":"Tenghui Ma","orcid":"https://orcid.org/0009-0001-3995-8596"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tenghui Ma","raw_affiliation_strings":["Fudan University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-3995-8596","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102966178","display_name":"Jihu Guo","orcid":"https://orcid.org/0009-0002-9811-0234"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihu Guo","raw_affiliation_strings":["Fudan University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-9811-0234","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100732619","display_name":"Wei Gao","orcid":"https://orcid.org/0000-0002-7048-1722"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Gao","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-7048-1722","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134807126","display_name":"S Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sitian Lu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-3469-7136","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103041352","display_name":"Zhisheng Ye","orcid":"https://orcid.org/0000-0002-4568-0244"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhisheng Ye","raw_affiliation_strings":["Independent Researcher, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4568-0244","affiliations":[{"raw_affiliation_string":"Independent Researcher, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128831402","display_name":"Hanjing Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanjing Wang","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-3897-9820","affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010087030","display_name":"Dahua Lin","orcid":"https://orcid.org/0000-0002-8865-7896"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dahua Lin","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-8865-7896","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"179","last_page":"192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.3449000120162964,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.3449000120162964,"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"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.15860000252723694,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.09560000151395798,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.7692000269889832},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.7232000231742859},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.6711000204086304},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6413999795913696},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6230000257492065},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5024999976158142}],"concepts":[{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.7692000269889832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440000176429749},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7232000231742859},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.6711000204086304},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6413999795913696},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6230000257492065},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36629998683929443},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3630000054836273},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3059000074863434},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2797999978065491},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26179999113082886}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3806645.3807815","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806645.3807815","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 35th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3806645.3807815","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806645.3807815","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 35th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2045271686","https://openalex.org/W2149207009","https://openalex.org/W2895690683","https://openalex.org/W2930500175","https://openalex.org/W2969388332","https://openalex.org/W3019389960","https://openalex.org/W3204998121","https://openalex.org/W4220741164","https://openalex.org/W4386840193","https://openalex.org/W4390263770","https://openalex.org/W4393406906","https://openalex.org/W4394923298","https://openalex.org/W4398796293","https://openalex.org/W4400484818","https://openalex.org/W4412944830","https://openalex.org/W4413757087","https://openalex.org/W4413757119","https://openalex.org/W4414210324","https://openalex.org/W4417070545"],"related_works":[],"abstract_inverted_index":{"Hybrid":[0],"parallelism":[1],"underpins":[2],"large-scale":[3],"LLM":[4],"training":[5,28],"across":[6,24],"tens":[7],"of":[8,10],"thousands":[9],"GPUs.":[11],"At":[12],"such":[13],"scale,":[14],"hardware":[15],"failures":[16,65],"on":[17],"individual":[18,69],"devices":[19],"lead":[20],"to":[21,75],"performance":[22,41],"skew":[23,42],"devices,":[25],"diminishing":[26],"overall":[27],"efficiency.":[29],"Existing":[30],"resilient":[31,81],"systems":[32],"overlook":[33],"sequence":[34,55],"length":[35,56],"variability":[36,57],"in":[37,71],"datasets":[38],"and":[39,63,79],"device":[40],"under":[43],"hybrid":[44,72],"parallelism.":[45],"As":[46],"a":[47],"result,":[48],"(1)":[49],"iteration":[50],"time":[51],"fluctuations":[52],"induced":[53],"by":[54],"can":[58],"trigger":[59],"spurious":[60],"fail-slow":[61],"detections,":[62],"(2)":[64],"are":[66],"mitigated":[67],"through":[68],"adaptations":[70],"parallelism,":[73],"leading":[74],"unnecessary":[76],"detection":[77],"overhead":[78],"inefficient":[80],"training.":[82]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-12T00:00:00"}