most citedMixNet: A Runtime Reconfigurable Optical-Electrical Fabric for Distributed Mixture-of-Experts Training

13 citations · 13 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse

Yingsheng Geng, Yuchong Gao, Weihong Wu +2

The increasing complexity of AI tasks has shifted the paradigm from monolithic models toward multi-agent large language model (LLM) systems. However, these collaborative architectu…