{"id":"W4409047962","doi":"10.1145/3721146.3721940","title":"Accelerating MoE Model Inference with Expert Sharding","year":2025,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Inference; Computer science; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009983683,0.00008857012,0.00009595059,0.00006710357,0.0001105341,0.0002321031,0.0006034761,0.00002946556,0.00001040105],"category_scores_gemma":[0.00002517434,0.00006763798,0.00001890922,0.0002146039,0.000009689691,0.0005240368,0.0003127705,0.00008896374,0.00000595864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002874236,"about_ca_system_score_gemma":0.0001137518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004965136,"about_ca_topic_score_gemma":0.00001289824,"domain_scores_codex":[0.9992158,0.00001078148,0.0001322188,0.0003140116,0.000139665,0.0001875427],"domain_scores_gemma":[0.9994061,0.00004744636,0.00002280563,0.0004331041,0.00005538877,0.00003516173],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001800777,0.00001510578,0.0009705853,0.000009831931,0.00001181237,0.000002892286,0.0009915896,0.139097,0.001905922,0.798299,0.0003935522,0.05830088],"study_design_scores_gemma":[0.0001094833,0.000006277022,0.00003557076,0.00003934102,8.456676e-7,8.845485e-7,0.00003548917,0.9928583,0.002442945,0.004290414,0.00009070522,0.00008973636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01080932,0.00003416335,0.9271511,0.0008723771,0.00006472537,0.00006264815,8.120436e-8,0.0002233913,0.06078218],"genre_scores_gemma":[0.6004913,0.000002200985,0.397393,0.000919099,0.00001148037,0.00001023333,1.157343e-7,0.000002031419,0.001170505],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8537613,"threshold_uncertainty_score":0.2758197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06416343562599425,"score_gpt":0.3062068170236703,"score_spread":0.2420433813976761,"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."}}