← DeepSeek V3 inference
What podcasts say about DeepSeek V3 inference
Every statement, with the speaker, the exact quote and the moment it was said.
What experts have said about DeepSeek V3 inference
1 statement · 1 positive
Sparse-model inference may be most efficient above 2,400 concurrently generated sequences.
“the optimal inference batch size for a sparse model like say, deep seq v3 is more than 2,400 concurrent sequences being generated at once.”
Open the episode · 8 Predictions for the Era of Continual LearningListen at 7:22
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.