activity
20232026
most citedMPIC: Position-Independent Multimodal Context Caching System for Efficient MLLM Serving

1 citations · 1 across the 10 of their papers we have counts for

collaborators
Showing 2026 · cs.DCShow all

1 paper · 2 filters

cs.DC2026

UBEP: Re-architecting Expert Parallelism Communication Library for Production Superpods

Yipeng Liu, Chang Liu, Si Shen +16

The deployment of Mixture-of-Experts (MoE) models on production high-bandwidth superpods, such as NVIDIA's NVL72/576 and Huawei's CloudMatrix384, introduces critical challenges bey…