← DeepSeek V3
What podcasts say about DeepSeek V3
Every statement, with the speaker, the exact quote and the moment it was said.
What experts have said about DeepSeek V3
1 statement · 1 positive
Optimal sparse-model inference batches exceed 2,400 concurrent 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.