LP
LLM prefill and decode
Topic
What experts have said about LLM prefill and decode
1 statement · 1 neutral
Prefill is compute-limited, whereas decode is memory-bandwidth-limited.
“prefill is compute limited and decode is memory bandwidth limited”
Open the episode · Reiner Pope – The math behind how LLMs are trained and servedListen at 1:45:11
Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.