Enabling real-time inference acceleration on AMD adaptive SoCs, FPGAs and acceleration cards

AMD Vitis AI

Overview

AMD Vitis™ AI software is an AI inference development platform for AMD devices, boards, and Alveo™ data center acceleration cards. It consists of a rich set of AI models, an optimized neural network processing unit (NPU) core, tools, libraries, and example designs. It is designed with high efficiency and ease of use in mind, empowering developers to unleash the full potential of AI acceleration.

Development Flow

  • Support for mainstream frameworks and the latest models capable of diverse deep learning inference, CNN, and generative large language Models
  • Powerful quantizer tools for optimal model accuracy and processing efficiency
  • Easy compilation flow and high-level APIs to achieve fast deployment of custom models
  • Highly efficient and configurable NPU cores to meet different needs for throughput, latency, and power at the edge, endpoints, and in the cloud
图像缩放
Vitis AI User Application Diagram

Get to Know Vitis AI Software

Deployment

Edge Deployment

Vitis AI software enables powerful computing performance, high flexibility, and optimal power consumption for edge applications across various industries—automotive, industrial, medical, video analysis, and more.

Browse AMD and Partner Edge Platforms
On-Premises Deployment

Vitis AI software enables competitive AI inference performance on AMD Alveo data center accelerator cards—designed to deliver ultra-low-latency, high throughput, and high flexibility for modern data center applications.

Browse AMD Alveo Accelerator Cards

Support

Looking to share your AI experiences, ask questions, and help solve issues? Check out the Vitis AI Community Forum.

Sign Up for Vitis AI News

Get the latest Vitis AI news and keep up-to-date on the latest release.

Sign Up