Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nawrot, Piotr, Łańcucki, Adrian, Chochowski, Marcin, Tarjan, David, Ponti, Edoardo M.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!