1 citations · 1 across the 4 of their papers we have counts for
4 papers
Analytical Provisioning for Attention-FFN Disaggregated LLM Serving under Stochastic Workloads
Chendong Song, Meixuan Wang, Hang Zhou +5
Attentio-FFN disaggregation (AFD) is an emerging architecture for LLM decoding that separates state-heavy, KV-cache-dominated Attention computation from stateless, compute-intensiv…
Observation of vector charmoniumlike states and search for in at BESIII
Hang Zhou
We present the recent measurements of the process carried out by the BESIII experiment. A new decay mode is firstly identified by BES…
A New Adaptive Gradient Method with Gradient Decomposition
Zhou Shao, Tong Lin
Adaptive gradient methods, especially Adam-type methods (such as Adam, AMSGrad, and AdaBound), have been proposed to speed up the training process with an element-wise scaling term…
Normal complex symmetric weighted composition operators on the Hardy space
Hang Zhou, Ze-Hua Zhou
In this paper, we investigate the normal weighed composition operators which is symmetric, symmetric and symmetric on the Ha…