Is this page helpful?

Method 5: Zip File Installation (Windows)#

Recommended for: C++ and Python development on Windows, custom installation paths

Advantages:

✓ High flexibility in installation location
✓ No administrator privileges needed for installation
✓ Multiple versions can coexist
✓ Includes C++ headers

Limitations:

✗ Requires manual dependency management
✗ Manual PATH configuration
✗ No automatic updates
✗ More complex setup than pip

Platform Support#

Supported Operating Systems:

  • Windows 10 (x64)

  • Windows 11 (x64)

  • Windows Server 2022 (x64)

  • Windows 11 (Arm64): restricted to compute capability 12.1 and DLA (Deep Learning Accelerator) engines only. Refer to the TensorRT Support Matrix for the platform row.

Prerequisites:

  • CUDA Toolkit installed (zip file or package manager)

Installation Steps#

Step 1: Download the TensorRT zip file

From the TensorRT download page, download the TensorRT zip file for Windows.

Example filename: TensorRT-Enterprise-11.4.1.x-Windows-amd64-cuda-13.4-Release-external.zip

Step 2: Choose installation directory

Choose where you want to install TensorRT. This zip file will install everything into a subdirectory called TensorRT-11.x.x.x. This new subdirectory will be called <installpath> in the steps below.

Step 3: Extract the zip file

Unzip the TensorRT-Enterprise-11.x.x.x-Windows-amd64-cuda-x.x-Release-external.zip file to the location you chose.

Replace amd64 with arm64 for Windows on ARM.

Step 4: Set environment variables

Add the TensorRT library files to your system PATH by adding <installpath>\bin to your system PATH environment variable. Follow these steps:

  1. Press the Windows key and search for environment variables. You should then be able to click Edit the System Environment Variables.

  2. Click Environment Variables… at the bottom of the window.

  3. Under System variables, select Path and click Edit….

  4. Click either New or Browse to add a new item that contains <installpath>\bin.

  5. Continue to click OK until all the newly opened windows are closed.

Step 5 (Optional): Install Python wheels

Install one of the TensorRT Python wheel files from <installpath>\python. Replace cp3x with the desired Python version (such as cp310 for Python 3.10). On Windows on ARM, also replace win_amd64 with win_arm64 in each command below.

PowerShell does not expand wildcards in arguments passed to an external program, so each command below resolves the wheel with Get-Item first:

cd <installpath>\python
python.exe -m pip install (Get-Item tensorrt-*-cp3x-none-win_amd64.whl)

cd <installpath>\python
python.exe -m pip install (Get-Item tensorrt_lean-*-cp3x-none-win_amd64.whl)

cd <installpath>\python
python.exe -m pip install (Get-Item tensorrt_dispatch-*-cp3x-none-win_amd64.whl)

Verification#

For quick checks that apply to every install method, refer to Verifying Your Installation in the installation overview. The steps below are specific to zip archives on Windows.

C++ Verification:

Open a new PowerShell window so that the updated PATH takes effect, then confirm that <installpath>\bin is on PATH:

trtexec --help

Samples and sample data are only available from GitHub. Refer to the TensorRT Sample Support Guide for how to obtain the samples from GitHub and build the samples using CMake. The instructions to prepare the sample data can be found within the samples README.md.

If you want to use TensorRT in your project, ensure that the following is present in your Visual Studio Solution project properties:

  1. <installpath>\bin has been added to your PATH variable and is present under VC++ Directories > Executable Directories.

  2. <installpath>\include is present under C/C++ > General > Additional Directories.

  3. nvinfer_11.lib and any other LIB files your project requires are present under Linker > Input > Additional Dependencies.

Note

You should install Visual Studio 2022 or later to build the included samples. The community edition is sufficient to build the TensorRT samples.

Python Verification:

import tensorrt as trt
print(trt.__version__)
assert trt.Builder(trt.Logger())

Troubleshooting#

For install-wide diagnostics (CUDA, drivers, samples, and runtime failures), refer to Troubleshooting. Method-specific issues for Windows zip installs:

Issue: DLL load failed: The specified module could not be found

  • Solution: Ensure PATH includes <installpath>\bin (where the TensorRT runtime DLLs live) and that CUDA libraries are in your system PATH. The <installpath>\lib directory holds the .lib import libraries used at link time, not the runtime DLLs.

Issue: Visual Studio cannot find TensorRT headers

  • Solution: Add <installpath>\include to your project’s Additional Include Directories in Visual Studio project properties.

Issue: Linker errors when building samples

  • Solution: Add <installpath>\lib to your project’s Additional Library Directories in Visual Studio project properties.