activity
20232026
most citedProSA: Assessing and Understanding the Prompt Sensitivity of LLMs

9 citations · 36 across the 41 of their papers we have counts for

collaborators
Showing cs.DCShow all

1 paper · 1 filter

cs.DC2026

NanoCP: Request-Level Dynamic Context Parallelism for Data-Expert Parallel Decoding

Jiefei Chen, Binbin Lin, Jinming Ma +9

Modern serving systems for Mixture-of-Experts (MoE) models adopt hybrid data-expert parallelism: expert parallelism (EP) shards experts across GPUs to scale capacity, while data pa…