Post by Yuchen Jin on X
Yuchen Jin@Yuchenj_UW
Xholy shit, DeepSeek is able to get 73.7k tokens/s input and 14.8k tokens/s output throughput per H800 node!
Their profit margin is 545%, while OpenAI is bleeding money despite charging so much??
that's how awesome their inference stack is.

4.7K likes101 repliesPosted Mar 1, 2025