> This page is for version 0.1.0.
> For other versions, use one of these documentation indexes:
> - 0.2.0 (Latest) (default): https://docs.nvidia.com/nim/computer-vision/semantic-split/0.2.0/llms.txt
> - 0.1.0: https://docs.nvidia.com/nim/computer-vision/semantic-split/0.1.0/llms.txt

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

# Prerequisites

This documentation describes the prerequisites for the Semantic Split C-RADIO NIM.

## Hardware Support

| **GPU** | **GPU Memory (GB)** | **\# of GPUs** |
| ------- | ------------------- | -------------- |
| L40S    | 48 GB               | 1              |

The Early Access release is specifically fine-tuned for L40S. In particular, NVEnc enabled hardware is required. Please contact us for inquiries on how the NIM could be extended to support more hardware configurations.

## Software

- With a Docker-supported operating system, install [Docker](https://docs.docker.com/engine/install/) - minimum version: 23.0.1

- Install [NVIDIA Drivers](https://www.nvidia.com/en-us/drivers/) - minimum version: 535. You can use the NVIDIA driver release 535.86 (or later R535), or 545.23 (or later R545) which are supported on L40S DataCenter GPUs.

- [Install](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html#installing-the-nvidia-container-toolkit) and [configure](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html#configuration) the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/index.html) - minimum version: 1.13.5

- Verify your container runtime supports NVIDIA GPUs by running the following:
    
    ```bash
    docker run --rm --runtime=nvidia --gpus all ubuntu nvidia-smi
    ```

For more information on enumerating multi-GPU systems, please see the NVIDIA Container Toolkit’s [GPU Enumeration Docs](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/docker-specialized.html?highlight=enumerate#gpu-enumeration)*.*

## NGC

You must have an authenticated NGC (NVIDIA GPU Cloud) account with access to both the respective NIM and the model checkpoints. Use the following procedure to log in to NGC, and set the `NGC_API_KEY` environment variable, so that you can pull images.

- Create an account on [NGC](https://catalog.ngc.nvidia.com/).

- Generate an [API Key](https://org.ngc.nvidia.com/setup/api-key). The following steps require your NGC API key.

- Authenticate local Docker with NGC by running the following code. For more details, see the [NGC authentication documentation](https://docs.nvidia.com/launchpad/ai/base-command-coe/latest/bc-coe-docker-basics-step-02.html).
    
    ```bash
    docker login nvcr.io
    Username: $oauthtoken
    Password: <NGC API key>
    ```

- Set the `NGC_API_KEY` environment variable in your shell.
    
    ```bash
    export NGC_API_KEY=<NGC API key>
    ```

## Supported Formats

| Input codecs               | H.264, HEVC, VP9, VP8, AV1 |
| -------------------------- | -------------------------- |
| Input pixel formats        | NV12/YUV420p               |
| Input container types      | MP4, MOV, WEBM             |
| Maximum input resolution   | 1080p                      |
| Output codec and container | H.264, MP4                 |
| Output resolution          | Same as input resolution   |