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
Posted on • Originally published at julsimon.Medium on
Video: Accelerate Transformer inference with AWS Inferentia 2
For further actions, you may consider blocking this person and/or reporting abuse
Top comments (0)