Skip to content

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

Mehran Salmani, Saeid Ghafouri, Alireza Sanaee, Kamran Razavi, Max Mhlhuser, Joseph Doyle, Pooyan Jamshidi, Mohsen Sharifi

Year2023
ProceedingsEuroMLSys@EuroSys

Browse the full EuroSys paper archive.