"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic ..."

Huiqiang Jiang et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2407.02490

access: open

type: Informal or Other Publication

metadata version: 2024-08-07

a service of  Schloss Dagstuhl - Leibniz Center for Informatics