HybridSpec: Exploiting Hybrid-bonding Memory to Accelerate LLM Serving through Heterogeneous Architecture and Speculative Decoding

Zongle Huang, Wenbin Jia, Yaolei Li, Xinyuan Lin, Shupei Fan, Chen Tang, Shuwen Deng, Yongpan Liu
June 2026
Type
Conference paper
Publication
Proceedings of the 53rd Annual International Symposium on Computer Architecture
Shuwen Deng
Shuwen Deng
Associate Professor