FlowSpec: Continuous Pipelined Speculative Decoding for Efficient Distributed LLM Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Xing, Luo, Lizhuo, Tang, Ming, Huang, Chao, Chen, Xu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!