"Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs."

Jaewoo Yang, Hayun Kim, Younghoon Kim (2024)

Details and statistics

DOI: 10.48550/ARXIV.2405.14428

access: open

type: Informal or Other Publication

metadata version: 2024-06-19

a service of  Schloss Dagstuhl - Leibniz Center for Informatics