"Improving Throughput-oriented Generative Inference with CPUs."

Daon Park, Sungbin Jo, Bernhard Egger (2023)

Details and statistics

DOI: 10.1145/3609510.3609815

access: closed

type: Conference or Workshop Paper

metadata version: 2024-05-05

a service of  Schloss Dagstuhl - Leibniz Center for Informatics