Quick reference

• The official TensorRT docker image.

• Maintained by: openEuler CloudNative SIG.

• Where to get help: openEuler CloudNative SIG, openEuler.

TensorRT | openEuler

Current TensorRT docker images are built on the openEuler. This repository is free to use and exempted from per-user rate limits.

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

It includes the sources for TensorRT plugins and ONNX parser, as well as sample applications demonstrating usage and capabilities of the TensorRT platform. These open source software components are a subset of the TensorRT General Availability (GA) release with some extensions and bug-fixes.

Learn more on NVIDIA TensorRT.

Supported tags and respective Dockerfile links

The tag of each tensorrt docker image is consist of the version of tensorrt and the version of basic image. The details are as follows

Tags	Currently	Architectures
10.16-oe2403sp3	TensorRT 10.16 on openEuler 24.03-LTS-SP3	amd64, arm64

Usage

In this usage, users can select the corresponding {Tag} based on their requirements.

• Pull the openeuler/tensorrt image from docker

  docker pull openeuler/tensorrt:{Tag}
  

• Start a TensorRT interactive container

  docker run -it --gpus all openeuler/tensorrt:{Tag} /bin/bash
  

• Use trtexec to build an optimized engine from an ONNX model

  trtexec --onnx=model.onnx --saveEngine=model.engine
  

• Use TensorRT Python API

  import tensorrt as trt
  logger = trt.Logger(trt.Logger.WARNING)
  builder = trt.Builder(logger)
  

• To get an interactive shell

  docker exec -it my-tensorrt /bin/bash
  

Question and answering

If you have any questions or want to use some special features, please submit an issue or a pull request on openeuler-docker-images.