Valency Hub
alphaFeedback
PDF

WorksComputer Science

HybridSpec: Throughput-Aware Speculative Decoding for Hybrid GDN-MoE Models

Haiyu Wang, Sai Qian Zhang, Zechun Liu, Steven Li

Published Fresh — added to the Hub within the last 30 daysv1

Publication details
License
CC BY 4.0
Status
Published
AI contributions
  • generative AI tools
View details
Machine checks

No machine checks are available from the Hub API for this paper.