Plain-AyI
← All projects
Running AI at scale

TensorRT

NVIDIA's toolkit for making trained AI models run faster on NVIDIA graphics cards.

New this week

What it does

TensorRT is a software kit from NVIDIA for inference, which means running an AI model after it has been trained. It is designed to make models run quickly on NVIDIA graphics cards (GPUs).

This repository holds the open-source parts of TensorRT: add-ons called plugins, a tool that reads models saved in the common ONNX format, and sample apps. The main TensorRT release is downloaded separately from NVIDIA.

It is aimed at engineers who put AI models into products and need them to respond fast.

Who it's for

Software engineers and AI teams who deploy models on NVIDIA hardware.

Can I use it without coding?

Developers only. It is a programming toolkit that needs an NVIDIA GPU and developer tools. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Linux, Windows
Computer
Works best on a powerful computer or one with a graphics card (GPU)
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it