Reducing Language Model Inference Latency using CPU-Assisted Serving

Open Webpage

Theodoros Aslanidis, Sokol Kosta, Raffaele Montella, Spyros Lalis, Dimitris Chatzopoulos

Published: 2026, Last Modified: 02 May 2026EuroMLSys@EuroSys 2026EveryoneRevisionsBibTeXCC BY-SA 4.0