Amazon Inferentia logo

Amazon Inferentia

Runs machine learning models efficiently across popular deep learning frameworks.

Made by Amazon Web Services (AWS)

    What is Amazon Inferentia?

    Amazon Inferentia is a machine learning inference chip engineered to deliver high-performance computing at a low cost. This specialized hardware is designed to support popular deep learning frameworks, including TensorFlow, Apache MXNet, and PyTorch, as well as models utilizing the ONNX format. With its robust processing capabilities and efficient design, Amazon Inferentia aims to enable organizations to accelerate their machine learning workloads and drive impactful insights from their data

    Highlights

    • Supports leading deep learning frameworks: TensorFlow, Apache MXNet, PyTorch
    • Compatibility with ONNX format models
    • High-performance computing for machine learning inference
    • Cost-effective solution for accelerating ML workloads

    Social