Sitemap

Video: Accelerate Transformer inference with AWS Inferentia 2

Apr 14, 2023

AWS Inferentia2 is now generally available, and I couldn’t resist testing it with BERT models and comparing results with Inferentia1.

This thing is FAST and looks very cost-effective. Check it out!

Julien Simon
Julien Simon

Written by Julien Simon

AI Operating Partner @ Fortino Capital (www.fortinocapital.com) - Ex-Arcee AI, Hugging Face, AWS - Tech, Cloud, AI, VC, PE, Investing - https://www.airealist.ai