"Opara: Exploiting Operator Parallelism for Expediting DNN Inference on GPUs."

Aodong Chen et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2312.10351

access: open

type: Informal or Other Publication

metadata version: 2024-06-13

a service of  Schloss Dagstuhl - Leibniz Center for Informatics