is quite CPU consuming. What solutions do I have in order to improve the performance of my API, would thread pooling improve it?
What is BERT model?
https://github.com/google-research/bert
try using Albert
Thank you! Although that's not a direct fix to the issue. I woud like to know which is the most efficient way to design a system, which some services requires high demand of CPU, like in the previous case I mentioned.
Обсуждают сегодня