Technologies new blogTechnologies new blog

Amazon announces preview of new Inf2 instances designed for larger models

AWS CEO Adam Selipsky made the announcement today at AWS re:Invent in Las Vegas As Selipsky explained, “Inf1 is great for small-to-medium complexity models, but for larger models, customers have often relied on more powerful instances because they don’t actually have the optimal resource configuration for their inference workloads,” he told the AWS re:Invent audience. They did this because up until now, there simply wasn’t another solution available to help bring down the cost and complexity of processing these larger workloads. “You want to choose the solution that is the best fit for your specific needs, which is why today I’m excited to announce a preview of the Inf2 instance powered by our new inferential two chip,” he said. For folks who need that extra power, Inf2 provides it. “Customers can deploy a 175 billion parameter model for inference on a single instrument with four times higher throughput and 1/10 the latency of Inf1 instances,” he said. The new instances are available in preview starting today. aws-reinvent-2022-banner-6 Amazon announces preview of new Inf2 instances designed for larger models by Ron Miller originally published on TechCrunch

Source

Press ESC to close