"Hydragen: High-Throughput LLM Inference with Shared Prefixes."

Jordan Juravsky et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2402.05099

access: open

type: Informal or Other Publication

metadata version: 2024-02-14

a service of  Schloss Dagstuhl - Leibniz Center for Informatics