Product
Amazon Inferentia
IT InfrastructureOther IT Infrastructure
The custom-designed chip for machine learning inference at scale.
☆☆☆☆☆ 0.0 Based on 0 Reviews
Amazon Inferentia
Learn More
About the Amazon Inferentia
Amazon Inferentia is a custom-built, high-performance machine learning inference chip designed by Amazon Web Services (AWS) to provide the lowest cost per inference in the cloud. It powers Amazon EC2 Inf1 and Inf2 instances, which are optimized for running machine learning models for applications like natural language processing, computer vision, and recommendation engines. By using the AWS Neuron SDK, developers can easily compile and run their machine learning models from popular frameworks like TensorFlow and PyTorch with minimal code changes, allowing for high throughput and low latency.