AWS launches its custom Inferentia inferencing chips

sonos sonos One (Gen 2) - Voice Controlled Smart Speaker with Amazon Alexa Built-in - Black read more

At its re:Invent conference, AWS today announced the launch of its Inferentia chips, which it initially announced last year. These new chips promise to make inferencing, that is, using the machine learning models you pre-trained earlier, significantly faster and cost effective.

As AWS CEO Andy Jassy noted, a lot of companies are focussing on custom chips that let you train models (though Google and others would surely disagree there). Inferencing tends to work well on regular CPUs, but custom chips are obviously going to be faster. With Inferentia, AWS offers lower latency and three times the throughput at 40% lower cost--per inference compared to a regular G4 instance on EC4.

The new Inf1 instances promise up to 2,000 TOPS and feature integrations with TensorFlow, PyTorch and MXNet, as well as the ONNX format for moving models between frameworks. For now, it's only available in the EC2 compute service, but it wil come to AWS's container services and its SageMaker machine learning service soon, too.

d2bc8cebb6738dbd044989050073b799

sonos sonos One (Gen 2) - Voice Controlled Smart Speaker with Amazon Alexa Built-in - Black read more
spaceball.gif

727faeb0b5de21dc6aca460274f88ce2

all right reserved for yahoo news

Get the latest news delivered to your inbox

Follow us on social media networks

PREV Amazon says Cyber Monday was its biggest shopping day ever
NEXT The best laptops and 2-in-1s this holiday season