{"id":"W4396949252","doi":"10.1109/isqed60706.2024.10528703","title":"sLLM: Accelerating LLM Inference using Semantic Load Balancing with Shared Memory Data Structures","year":2024,"lang":"en","type":"article","venue":"","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Inference; Load balancing (electrical power); Parallel computing; Programming language; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00221946,0.001485984,0.0009491633,0.001753078,0.001501183,0.002887721,0.005079719,0.001355393,0.006787199],"category_scores_gemma":[0.008967507,0.001129163,0.001282357,0.001974611,0.001181658,0.008523818,0.004396872,0.002121252,0.003072544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001907501,"about_ca_system_score_gemma":0.003894438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0137458,"about_ca_topic_score_gemma":0.02236006,"domain_scores_codex":[0.998192,0.0003936774,0.0001612146,0.0004809348,0.0005906873,0.0001814274],"domain_scores_gemma":[0.9966195,0.001101375,0.000208824,0.001401912,0.0005070579,0.0001613048],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001913072,0.001078633,0.009884749,0.001111551,0.000716116,0.0006229202,0.001509282,0.1076775,0.04907418,0.03502977,0.07597804,0.7154042],"study_design_scores_gemma":[0.0001736096,0.00009397916,0.0005804387,0.00003139016,0.000104693,0.0001003464,0.0001939604,0.9273347,0.02843921,0.02830128,0.0145767,0.00006969315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03910353,0.0008007706,0.7975998,0.000692955,0.0002930965,0.0002686936,0.001212864,0.1549946,0.005033685],"genre_scores_gemma":[0.3482634,0.0003382115,0.6368306,0.0005270508,0.0001273216,0.000290837,0.004132445,0.004492628,0.004997612],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0137458,"threshold_uncertainty_score":0.02733153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09859305686494269,"score_gpt":0.3239352768110861,"score_spread":0.2253422199461434,"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."}}