Installing TensorRT#
This guide provides step-by-step instructions for installing TensorRT using various methods. Choose the installation method that best fits your development environment and deployment needs.
Before You Begin: Ensure you have reviewed the Prerequisites to confirm your system meets all requirements.
Installation Method Comparison#
Quick Comparison Table:
Method |
Best For |
Requires Root |
C++ Headers |
Multi-Version |
Installation Time |
|---|---|---|---|---|---|
pip (Python) |
Python development |
No |
No |
Yes (venv) |
⚡ Fastest (~2 min) |
Debian/RPM |
System-wide install |
Yes |
Yes |
No |
🔵 Fast (~5 min) |
Tar/Zip |
Multiple versions |
No |
Yes |
Yes |
🟡 Moderate (~10 min) |
Container (NGC) |
Isolated environments |
No (Docker) |
Yes |
Yes |
⚡ Fastest (~5 min) |
Choosing Your Installation Method#
Choose pip if you:
Are developing primarily in Python
Want the fastest installation
Are working in a Python virtual environment
Do not need C++ development headers
Choose Debian/RPM if you:
Want system-wide installation with automatic updates
Need C++ development support
Have sudo/root access
Prefer standard Linux package management
Choose Tar/Zip if you:
Need multiple TensorRT versions simultaneously
Want control over installation location
Are installing without root privileges
Need C++ headers but want flexibility
Choose Container if you:
Want a pre-configured environment
Are deploying in Kubernetes or Docker
Need consistent environments across systems
Want to avoid dependency management
Understanding TensorRT Runtime Options#
TensorRT offers three runtime configurations with different capabilities and footprint sizes:
- Full Runtime (Recommended for Development)
Builder and runtime functionality (~2 GB)
Packages:
tensorrt(pip),tensorrt(deb/rpm),TensorRT-*(tar/zip)
- Lean Runtime (Recommended for Production Deployment)
Runtime-only for pre-built engines (~500 MB)
Packages:
tensorrt_lean(pip),tensorrt-lean(deb/rpm)Note: Engines must be built with version-compatible builder flag
- Dispatch Runtime (Recommended for Minimal Footprint Deployment)
Minimal runtime for pre-built engines (~200 MB)
Packages:
tensorrt_dispatch(pip),tensorrt-dispatch(deb/rpm)Note: Engines must be built with version-compatible builder flag
Component Versioning#
TensorRT is a product made up of separately versioned components. The product version conveys important information about the significance of new features, while the library version conveys information about the compatibility or incompatibility of the API.
The following table shows product versions and corresponding component library versions for TensorRT 10.16.1, illustrating semantic versioning patterns for each component.
Product/Component |
Previous Released Version |
Current Version |
Version Description |
|
|---|---|---|---|---|
TensorRT product |
10.16.0 |
10.16.1 |
|
|
|
10.16.0 |
10.16.1 |
|
|
|
10.16.0 |
10.16.1 |
|
|
|
10.16.0 |
10.16.1 |
|
|
|
|
10.16.0 |
10.16.1 |
|
|
|
10.16.0 |
10.16.1 |
|
|
|
10.16.0 |
10.16.1 |
|
|
|
10.16.0 |
10.16.1 |
|
Downloading TensorRT#
Before installing with Debian (local repo), RPM (local repo), Tar, or Zip methods, you must download TensorRT packages.
Tip
For pip installation: Skip this section. The pip method downloads packages automatically from PyPI.
Prerequisites:
NVIDIA Developer Program membership (free)
Account login
Download Steps:
Click Download Now.
Select TensorRT version 10.16.1 (or your target version).
Accept the license agreement.
Download the package for your platform:
Linux x86-64: Debian local repo (
.deb), RPM local repo (.rpm), or Tar (.tar.gz)Linux ARM SBSA and JetPack: Debian local repo (
.deb) or Tar (.tar.gz)Windows x64: Zip (
.zip)