Mixture-of-Experts (MoE) inference on memory-constrained edge platforms is often dominated by expert-weight movement rather than computation. Although each token activates only a small subset of experts, routing is input-dependent, so all experts must remain accessible and memory movement dominates latency. Existing ap...
Cong-Wei Zhang, Youming Tao, Yi-Fei Zou et al.· Proceedings of the 32nd Annu...· 1 citation
Experiments on synthetic topologies and trace-driven workloads show that the proposed egress-side tail-risk analysis framework meets system-level tail constraints while providing more robust and interpretable capacity planning than mean-centric baselines.
Hang Zhao, Sheng-Ling Wang, Ke Chao et al.· IEEE Transactions on Mobile...· 0 citations
An SFC Deployment and Scheduling strategy based on the Soft Actor-Critic (SAC) algorithm, named SAC-DS, which integrates SFC deployment, component sharing, and scheduling into a unified framework, effectively improving system throughput while minimizing overall deployment costs, thereby enhancing user experience.
Xue-Jian Chi, Yi-Fei Zou, Cong-Wei Zhang et al.· IEEE Transactions on Mobile...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
