Ghidorah: Fast LLM Inference on Edge with Speculative Decoding and Hetero-Core Parallelism

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wei, Jinhui, Huang, Ye, Zhou, Yuhui, Jiang, Jiazhi, Du, Jiangsu, Lu, Yutong
Format:	Preprint
Published:	2025
Subjects:	Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2505.23219