{"id":"W4401752634","doi":"10.1109/icdcs60910.2024.00017","title":"When the Edge Meets Transformers: Distributed Inference with Transformer Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Transformer; Inference; Computer science; Electrical engineering; Artificial intelligence; Engineering; Voltage","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":[0.001559888,0.000852349,0.0009462368,0.0005295227,0.0007252372,0.002177406,0.002177858,0.001035995,0.002961342],"category_scores_gemma":[0.009077764,0.0007827083,0.0009410357,0.0006018064,0.001186355,0.005407398,0.002392053,0.002259168,0.0007120025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009783328,"about_ca_system_score_gemma":0.002000853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008781101,"about_ca_topic_score_gemma":0.01478952,"domain_scores_codex":[0.9990484,0.0002354116,0.00005042802,0.000319047,0.0002130173,0.0001336362],"domain_scores_gemma":[0.9971529,0.001358599,0.0001675452,0.0008180119,0.0003418153,0.0001610655],"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":[0.0006745549,0.0001842028,0.006288608,0.0001690242,0.0001336389,0.0004774405,0.0003101212,0.7482686,0.008675547,0.08769157,0.007357542,0.1397691],"study_design_scores_gemma":[0.0000140029,0.00001735256,0.0000934261,0.000004967942,0.000009793852,0.00002600638,0.0000285124,0.9639647,0.001650526,0.03349515,0.0006893186,0.000006231237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03041842,0.0001728337,0.9647831,0.0003650097,0.00006986988,0.00004574206,0.0001616618,0.00182129,0.002162016],"genre_scores_gemma":[0.7302419,0.0002227187,0.2647784,0.0003406993,0.00007869867,0.0000754,0.0005951225,0.0004915647,0.003175468],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008781101,"threshold_uncertainty_score":0.01745999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02416374468594464,"score_gpt":0.249602737411759,"score_spread":0.2254389927258143,"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."}}