Beyond Task-Agnostic: Task-Aware Grouping for Communication-Efficient Multi-Task MoE Inference 文章

ArXiv CS.AI2026-06-02NEWSen作者: Zhiyao Xu, Aoxue Liu, Zhanjie Ding, Dan Zhao, Yong Jiang, Qing Li

Beyond Task-Agnostic: Task-Aware Grouping for Communication-Efficient Multi-Task MoE Inference · 相关事件