FI
Frontier-model inference parallelism
Topic
What experts have said about Frontier-model inference parallelism
1 statement · 1 positive
Inference should maximize expert parallelism within the scale-up domain and use little pipeline parallelism.
“you should increase your expert parallelism up to your scale up domain size and then do very little pipelining”
Open the episode · Reiner Pope – The math behind how LLMs are trained and servedListen at 1:13:10
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.
