SpecMamba: Accelerating Mamba Inference on FPGA with Speculative Decoding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhong, Linfeng, Xu, Songqiang, Wen, Huifeng, Xie, Tong, Guo, Qingyu, Wang, Yuan, Li, Meng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!