{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008648229,0.0001208985,0.00008403057,0.00002406415,0.0001465388,0.0003555437,0.0005836471,0.00003055443,0.00003758222],"category_scores_gemma":[6.149852e-7,0.00005862548,0.00005358008,0.0004381314,0.00006078564,0.0007348942,0.00001732283,0.0001467874,0.00003360625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000132609,"about_ca_system_score_gemma":0.00006759325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004191723,"about_ca_topic_score_gemma":0.00009337164,"domain_scores_codex":[0.9991545,0.00001376247,0.0001319696,0.000285912,0.0001794664,0.0002344022],"domain_scores_gemma":[0.9995065,0.0001042691,0.000009940345,0.0002810764,0.00003023709,0.00006796298],"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":[0.000003306101,0.00002225514,0.000003729054,0.00001252326,0.00002556093,0.000004965412,0.0007470533,0.002590626,0.0002366048,0.8884007,0.005062764,0.1028899],"study_design_scores_gemma":[0.0001216391,0.00006243768,0.00004006886,0.00004239668,0.00001753567,0.00002292007,0.00003646206,0.8443635,0.001238653,0.06622139,0.08763617,0.0001968791],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008802666,0.0002284065,0.9591084,0.02995666,0.00006265732,0.0002509241,0.00001261928,0.0002934897,0.009206621],"genre_scores_gemma":[0.994358,0.00008511366,0.004527132,0.0004304194,0.00003809317,0.00008871142,0.000008429608,0.00000746786,0.0004566001],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9934778,"threshold_uncertainty_score":0.3428515,"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."}}