Skip to content
AIMarketCap

AWS Inferentia2

Model

Second-generation AWS inference accelerator for large generative-AI and deep-learning models.

Released
May 22, 2023
Context window
—
Modality
—
Open source
—
API available
—
Releases
1

Releases

1
May 22, 2023Amazon EC2 Inf2 instances become generally availableAWS Inferentia2 · Inferentia 2

AWS launched Inferentia2-powered EC2 instances for large-scale generative-AI inference.