Get started
Author

Zongyuan Zhan

Observed names: Zhan, Zongyuan, ZongYuan Zhan
Observed institution: Huawei Technologies (China)
OpenAlex ID: A5113091867
HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference
2025 · Haoran Lin, Xianzhi Yu, et al. · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · 1
Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs
2025 · Tang, Yehui, Yin, Yichun, et al. · arXiv (Cornell University)
PDF
MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE
2025 · Zongle Huang, Lei Zhu, et al. · neural information processing systems
PDF
Works count: 3
Citation count: 1
H-index: 1
I10-index:
Year
Topic
Type