What is disaggregated prefill and decode in LLM inference?

Automated excerpt

What is disaggregated prefill and decode in LLM inference? Prefill is compute-bound, decode is memory-bound. Prefill is compute-bound and sets TTFT; decode is memory-bandwidth-bound and sets ITL/TPOT.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.