Login / Signup

Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems.

Mehran SalmaniSaeid GhafouriAlireza SanaeeKamran RazaviMax MühlhäuserJoseph DoylePooyan JamshidiMohsen Sharifi
Published in: EuroMLSys@EuroSys (2023)
Keyphrases
  • low latency
  • high accuracy
  • highly efficient
  • high throughput
  • real time
  • distributed systems
  • data sets
  • database systems
  • high bandwidth