"FP8-BERT: Post-Training Quantization for Transformer."

Jianwei Li et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2312.05725

access: open

type: Informal or Other Publication

metadata version: 2024-01-03

a service of  Schloss Dagstuhl - Leibniz Center for Informatics