"I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large ..."

Xing Hu et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2405.17849

access: open

type: Informal or Other Publication

metadata version: 2024-06-21

a service of  Schloss Dagstuhl - Leibniz Center for Informatics