AMD Inference Server

0.3.0

About

Introduction
Dependencies
- Docker Image
  - Base Image
  - Ubuntu Focal Repositories
  - Ubuntu PPAs
  - PyPI
  - Github
  - Others
  - Xilinx
  - AMD
- Included
- Downloaded Files
Roadmap
- 2022 Q1
- 2022 Q2
- 2022 Q3
- Future
Changelog
- Unreleased
  - Added
  - Changed
  - Deprecated
  - Removed
  - Fixed
- 0.2.0 - 2022-08-05
  - Added
  - Changed
  - Fixed
- 0.1.0 - 2022-02-08
  - Added

Quickstart

Inference
Deployment
Development

Libraries and API

C++
- Clients
  - gRPC
  - HTTP
  - Native
  - WebSocket
- Core
- Servers
Python
- Install the Python library
  - Build wheels
- API
REST Endpoints
Command-Line Interface
- Commands
- Options
- Sub-commands
  - attach
  - benchmark
  - build
  - clean
  - dockerize
  - get
  - install
  - list
  - make
  - run
  - start
  - test
  - up

Examples

Hello World - Python
Running ResNet50 - C++
Running ResNet50 - Python

Using the Server

Platforms
Deploying with Docker
Deploying with KServe
Performance Factors

Developers

Contributing
Architecture
AKS
- Introduction to AKS
- Using AKS in AMD Inference Server
Logs
- AMD Inference Server Logs
- Drogon Logs
Benchmarking
- XModel Benchmarking
- Kernel Simulation
Metrics
- Quickstart
Tracing
- Quickstart
Code Documentation
- Full API

AMD Inference Server

»
Platforms
View page source

Platforms¶

The AMD Inference Server supports a number of platforms:

CPUs - ZenDNN
GPUs - MIGraphX
FPGAs - Vitis AI

Previous Next

© Copyright 2022 Advanced Micro Devices, Inc.. Last updated on February 15, 2023.

Terms and Conditions | Privacy | Cookie Policy | Trademarks | Statement on Forced Labor | Fair and Open Competition | UK Tax Strategy | Inclusive Terminology | Cookies Settings

Built with Sphinx using a theme provided by Read the Docs.

Read the Docs v: 0.3.0

Languages: en

Versions: 0.1.0; 0.2.0; 0.3.0; main