How We Scaled Bert To Serve 1+ Billion Daily Requests on CPU

Roblox is a global online platform bringing millions of people together through play, with over 37 million daily active users and millions of games on the platform. Machine learning is a key part of our ability to scale important services to our massive community. In this talk, we share our journey of scaling our deep learning text classifiers to process 50k+ requests per second at latencies under 20ms. We will share how we were able to not only make BERT fast enough for our users, but also economical enough to run in production at a manageable cost on CPU.

Connect with us:

[kjkszpjab]

Great walkthrough, thanks! Do you use NVIDIA Triton inference server? It works with CPU applications as well. It may add some more optimizations