Jul 2026
Mixture-of-Experts Serving
A polynomial-time $O(\sqrt{\log k})$-competitive online algorithm, where $k$ is the number of GPUs beyond one per expert, and a matching $\Omega(\sqrt{\log k})$ barrier for the online dual problem underlying the analysis.
Zhiyi Huang, Qinpei Lou, Tao Xiao
· arXiv.org · 2 citations
· ⚡1