TY  CONF
TI  INFRASTRUCTURE-LEVEL NEURAL NETWORK INFERENCE OPTIMIZATION: MODEL SERVING PLATFORMS AND DISTRIBUTED COMPUTING
KW  neural network inference
KW  model serving
KW  Triton Inference Server
KW  Ray Serve
KW  vLLM
KW  dynamic batching
KW  PagedAttention
KW  autoscaling
KW  Kubernetes
KW  distributed computing
JO  MODELING INFORMATION SYSTEMS AND TECHNOLOGIES – 2026
AU  Merzlyakov, N.V.
AU  Semkin, A.A.
AU  Matviychuk, B.S.
AU  Sedykh, D.A.
AU  Dudnik, S.P.
AU  Vytovtov, P.D.
PY  2026
PB  FSBE Institution of Higher Education Voronezh State University of Forestry and Technologies named after G.F. Morozov