Prefill vs Decode: Two Phases, Two Bottlenecks
This story is from 2026-10-29. It is preserved in the archive; the latest stories are on the live feed.
In Part 1 the Word Factory read your whole question in one go, then typed the answer one token at a time. Reading was cheap per token. Typing was slow. In Part 2 we counted the math for one token, and found something odd: the same computer did 18 times more math per second when many tokens shared a…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-10-29 09:18 · DEV Community — Machine Learning
Prefill vs Decode: Two Phases, Two Bottlenecks