Decode Token Parallelism: Memory-Efficient Distributed Attention Parallelism for Scalable LLM Decoding

arXiv:2611.13293 · cs.DC, cs.CL, cs.LG · Submitted 2026-11-09 · Read on arXiv

cs.DC, cs.CL, cs.LG

Submitted: 2026-11-09

Updated: 2026-11-09

Terminology

Sources

Related papers