Xinyu Zhu

Xinyu Zhu

Auto-generated profile, based on publicly available information

Xinyu Zhu

HuaZhong University of Science and Technology, Wuhan, Hubei, China

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 July 2026
Verified
Conference Paper
Open access
RWRunze Wang
Runze Wang
QWQinggang Wang
Qinggang Wang
HLHaifeng Liu
Haifeng Liu
XZXinyu Zhu
Xinyu Zhu
CDChenggang Duan
Chenggang Duan
JXJingling Xue
Jingling Xue
Emerging tree-structured speculative decoding has been proposed as a promising alternative to conventional sequence-structured speculative decoding, offering a higher verification success rate and reduced inference latency while exhibiting characteristics of higher computational intensity. However, existing near-memory processing (NMP)-enabled heterogeneous accelerators for large language models (LLMs) typically place processing elements (PEs) on DRAM dies, resulting in limited computation capability, which prevents them from fully accelerating tree-structured speculative decoding. In response, we propose a hybrid-bonding (HB)-based heterogeneous accelerator for tree-structured speculative decoding, called HBSpec, which customizes PEs on the incorporated logic die to enhance NMP computation capacity. HBSpec features a communication-optimized data mapping policy to minimize cross-bank data access overhead inherent in the distributed-memory design adopted in HB. Furthermore, an arithmetic intensity-aware operator scheduler is designed to dynamically assign operators to the most suitable hardware units, while a Tree-KV pool management scheme is introduced to eliminate memory fragmentation caused by discarded speculative branches. Experimental results demonstrate that HBSpec achieves average throughput improvements of 15.56×, 2.36×, and 2.13× over the state-of-the-art NPU-only, NPU+LPDDR, and NPU+HB baselines, respectively.

14 November 2026
Verified
Conference Paper
Open access
DLDongxu Liu
Dongxu Liu
BZBing Zhu
Bing Zhu
XZXinyu Zhu
Xinyu Zhu
LZLong Zheng
Long Zheng
XLXiaoFei Liao
XiaoFei Liao
JXJingling Xue
Jingling Xue