Pith. sign in

Demystifying the communication characteristics for distributed transformer models

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.DC 2

years

2026 2

roles

background 1

polarities

background 1

representative citing papers

Diagnosing Overhead in Dispatch Operations: Cross-architecture Observatory

cs.DC · 2026-05-20 · conditional · novelty 6.0

Expert-parallel scaling leaves per-expert routing imbalance flat; mock-token benchmarks overestimate real-text imbalance and fake a batch-size trend; architectures split into data-resilient (MHA, Mamba-2) and persistently concentrated (MLA, GDN) classes.

citing papers explorer

Showing 2 of 2 citing papers.