A simulator predicts that four-way prefill/decode/attention/FFN disaggregation beats unified serving on prefill-heavy agentic workloads by up to 2.06x, but only with stage-specialized custom NPUs and rich enough hardware choices.
Deepseek-v4 technical report,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.DC 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference
A simulator predicts that four-way prefill/decode/attention/FFN disaggregation beats unified serving on prefill-heavy agentic workloads by up to 2.06x, but only with stage-specialized custom NPUs and rich enough hardware choices.