---
title: "Disaggregated prefill and decode with numbers"
description: "Calculate KV transfer bytes and time, size prefill and decode pools independently, and decide when disaggregation beats chunked prefill."
canonical_url: "https://fanout.sh/blog/disaggregated-prefill-and-decode"
md_url: "https://fanout.sh/blog/disaggregated-prefill-and-decode.md"
last_updated: "2026-08-16"
access: "public"
---

# Disaggregated prefill and decode with numbers

Calculate KV transfer bytes and time, size prefill and decode pools independently, and decide when disaggregation beats chunked prefill.

- Author: Suraj Gaud

- Published: 2026-08-16

- Track: Inference engineering

- Access: Fanout Pro

- Tags: disaggregated inference, prefill, decode, KV cache, LLM serving, TTFT, TPOT, goodput

The complete article body is available to Fanout Pro members on the canonical page.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md