Should You Split Decode? Disaggregation Across Future Models and Accelerators

arXiv:2611.08299 · cs.AR · Submitted 2026-11-05 · Read on arXiv

cs.AR

Submitted: 2026-11-05

Updated: 2026-11-05

Code: https://github.com/hao-ai-lab/FastAFD

Terminology

Sources

Related papers