← Single-user personalized inference
What podcasts say about Single-user personalized inference
Every statement, with the speaker, the exact quote and the moment it was said.
What experts have said about Single-user personalized inference
1 statement · 1 negative
Single-user personalized inference may be over 100 times less compute-efficient than batched inference.
“an individual user who's only running a batch size one may suffer more than two orders of magnitude worse efficiency on their compute.”
Open the episode · 8 Predictions for the Era of Continual LearningListen at 7:57
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.