ViFusion: In-Network Tensor Fusion for Scalable Video Feature Indexing
Yisu Wang, Yixiang Zhu, Xinjiao Li, Yulong Zhang, Ruilong Wu, Dirk Kutscher · 2025
Large-scale video feature indexing in datacenters is critically dependent on efficient data transfer. Although in-network computation has emerged as a compelling strategy for accelerating feature extraction and reducing overhead in distributed multimedia systems, harnessing advanced networking resources at both the switch and host levels remains a formidable challenge. These difficulties are compounded by heterogeneous hardware, diverse application requirements, and complex multipath topologies. Existing methods focus primarily on optimizing inference for large neural network models using specialized collective communication libraries, which often face performance degradation in network congestion scenarios.