"S2D: Sorted Speculative Decoding For More Efficient Deployment of Nested ..."

Parsa Kavehzadeh et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2407.01955

access: open

type: Informal or Other Publication

metadata version: 2024-08-09

a service of  Schloss Dagstuhl - Leibniz Center for Informatics