{"id":"W4408846465","doi":"10.1145/3689031.3717461","title":"Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization","year":2025,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Mist; Parallel computing; Parallelism (grammar); Training (meteorology); Computer architecture; Distributed computing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000594374,0.001320436,0.0008217448,0.0004559046,0.0005842037,0.0007561158,0.002278442,0.0008009276,0.003800168],"category_scores_gemma":[0.002376009,0.0005244996,0.0009150164,0.0006966737,0.0006524564,0.00202343,0.001599298,0.00170406,0.00148245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007876554,"about_ca_system_score_gemma":0.001956838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007776032,"about_ca_topic_score_gemma":0.01538401,"domain_scores_codex":[0.9994097,0.0001231747,0.00002956907,0.000188321,0.0001543538,0.00009488062],"domain_scores_gemma":[0.9989611,0.0005148666,0.00006353834,0.000230384,0.0001644461,0.0000655687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005213397,0.0004117159,0.002300404,0.000269664,0.0001411597,0.0002539632,0.0002561326,0.5888264,0.02285364,0.006465093,0.02172174,0.3559788],"study_design_scores_gemma":[0.00003194932,0.00004278971,0.0001068037,0.000003158721,0.000008834072,0.00002062677,0.0000204165,0.9930063,0.00338452,0.0023655,0.001003638,0.000005420009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06532726,0.0007915922,0.8874012,0.0004329736,0.0001390835,0.0001353187,0.0003913403,0.03997007,0.005411264],"genre_scores_gemma":[0.5543312,0.0002528162,0.4343969,0.0004647855,0.00008195491,0.0003986548,0.002045068,0.00193526,0.006093439],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007776032,"threshold_uncertainty_score":0.0154615,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0171281055888019,"score_gpt":0.2690719334659288,"score_spread":0.2519438278771269,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}