Multi-Bin Batching for Increasing LLM Inference Throughput

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guldogan, Ozgur, Kunde, Jackson, Lee, Kangwook, Pedarsani, Ramtin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!