> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/cudnn/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/cudnn/_mcp/server.

# Installing cuDNN Backend on Windows

## Installing the CUDA Toolkit for Windows

Refer to the following instructions for installing CUDA on Windows, including the CUDA driver and toolkit: [NVIDIA CUDA Installation Guide for Windows](https://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html).

## Downloading cuDNN Backend for Windows

cuDNN Backend is available at [https://developer.nvidia.com/cudnn](https://developer.nvidia.com/cudnn). Click on the green buttons that describe your target platform and choose one of the following installer formats:

* **Graphical Installation** (executable) - the graphical installer bundles the available per-CUDA cuDNN versions in one package, where the desired CUDA version can be selected at install time through the graphical user interface.
* **Tarball Installation** (zip) - per-CUDA cuDNN versions are provided as separate tarballs (zip) at [https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/windows-x86\_64/](https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/windows-x86_64/). These `.zip` archives do not replace the graphical installer and are not meant for general consumption, as they are not installers.

For each release, a JSON manifest is provided such as **redistrib\_9.x.y.z.json**, which corresponds to the cuDNN 9.x.y.z release label which includes the release date, the name of each component, license name, relative URL for each platform, and checksums.

Details on parsing these JSON files are described in [Parsing Redistrib JSON](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#parsing-redistrib-json).

## Installing cuDNN Backend for Windows Software

The following steps describe how to install the downloaded cuDNN Backend for Windows software. You must replace `9.x` and `9.x.y.z` with your specific cuDNN version.

**Graphical Installation**

Install cuDNN by executing the cuDNN installer and following the on-screen prompts.

**Tarball Installation**

In the following steps, the package directory path is referred to as `<packagepath>`.

1. Navigate to your `<packagepath>` directory containing the cuDNN package.

2. Unzip the cuDNN package.

   ```
   cudnn-windows-x86_64-*-archive.zip
   ```

3. Copy the following files from the unzipped package into the NVIDIA cuDNN directory.

   4. Copy `bin\cudnn*.dll` to `C:\Program Files\NVIDIA\CUDNN\v9.x\bin`.
   5. Copy `include\cudnn*.h` to `C:\Program Files\NVIDIA\CUDNN\v9.x\include`.
   6. Copy `lib\x64\cudnn*.lib` to `C:\Program Files\NVIDIA\CUDNN\v9.x\lib`.

4. Set the following environment variable to point to where cuDNN is located. To access the value of the `$(PATH)` environment variable, perform the following steps:

   8. Open a command prompt from the **Start** menu.
   9. Type `Run` and hit **Enter**.
   10. Issue the `control sysdm.cpl` command.
   11. Select the **Advanced** tab at the top of the window.
   12. Click **Environment Variables** at the bottom of the window.
   13. Add the NVIDIA cuDNN `bin` directory path to the PATH variable:

       ```text
       Variable Name: PATH
       Value to Add: C:\Program Files\NVIDIA\CUDNN\v9.x\bin
       ```

5. Add cuDNN to your Visual Studio project.

   15. Open the Visual Studio project, right-click on the project name in **Solution Explorer**, and choose **Properties**.
   16. Click **VC++ Directories** and append `C:\Program Files\NVIDIA\CUDNN\v9.x\include` to the **Include Directories** field.
   17. Click **Linker > General** and append `C:\Program Files\NVIDIA\CUDNN\v9.x\lib\x64` to the **Additional Library Directories** field.
   18. Click **Linker > Input** and append `cudnn.lib` to the **Additional Dependencies** field and click **OK**.

## Upgrading cuDNN

Navigate to the directory containing cuDNN and delete the old cuDNN `bin`, `lib`, and `header` files. Remove the path to the directory containing cuDNN from the `$(PATH)` environment variable. Reinstall a newer cuDNN version by following the steps in [Installing cuDNN On Windows](/installation/backend/windows#installing-cudnn-backend-for-windows-software).

## Python Wheels - Windows Installation

NVIDIA provides Python Wheels for installing cuDNN through `pip`, primarily for the use of cuDNN with Python. With this installation method, the cuDNN installation environment is managed via `pip`. Additional care must be taken to set up your host environment to use cuDNN outside the `pip` environment.

> **Note**
>
> Before issuing the following commands, you must replace `9.x.y.z` with your respective cuDNN version. On Windows, only the `x86_64` architecture is supported.

### Prerequisites

If your `pip` and `wheel` Python modules are not up-to-date, then use the following command to upgrade these Python modules. If these Python modules are out-of-date, then the commands which follow later in this section may fail.

```
py -m pip install --upgrade pip wheel
```

### Installing cuDNN with Pip

To install cuDNN for CUDA 13, run:

```
py -m pip install nvidia-cudnn-cu13
```

To install cuDNN for CUDA 12, run:

```
py -m pip install nvidia-cudnn-cu12
```

To install cuDNN for a specific release version, include the release version in the command. For example, to install cuDNN 9.x.y.z for CUDA 13, run:

```
py -m pip install nvidia-cudnn-cu13==9.x.y.z
```

To install cuDNN 9.x.y.z for CUDA 12, run:

```
py -m pip install nvidia-cudnn-cu12==9.x.y.z
```

> **Note**
>
> Only one CUDA toolkit version of cuDNN 9 can be installed at a time.