.. _support_matrix:

Support Matrix
==============

These support matrices list the supported hardware and software requirements of Jarvis.   

Jarvis Speech Skills 1.0.0-b.1 Beta
-----------------------------------

Hardware
^^^^^^^^

The following table shows the supported hardware for Jarvis Speech Skills 1.0.0 Beta.

.. +------------------+----------------------------------------------------+
.. |                  | **Hardware Compatibility**                         |
.. +------------------+----------------------------------------------------+
.. | GPU Model        | *. NVIDIA Turing T4                                |
.. |                  | *. NVIDIA Volta V100                               |
.. |                  | *. NVIDIA A100 GPU                                 |
.. +------------------+----------------------------------------------------+

.. raw:: html
    <style>
      .wy-table-responsive table th {
        white-space: normal;
      }
    </style>

.. list-table:: 
    :header-rows: 1
    :widths: 20 80

    * - 
      - Hardware Compatibility
    * - GPU Model
      - 
            **Preferred Deployment Platforms:**

            - `NVIDIA Volta V100 <https://www.nvidia.com/en-us/data-center/volta-gpu-architecture/>`_
            - `NVIDIA Turing T4 <https://www.nvidia.com/en-us/data-center/tesla-t4/>`_
            - `NVIDIA A100 GPU <https://www.nvidia.com/en-us/data-center/a100/>`_

            *Note: Jarvis is supported on any Volta or later NVIDIA GPU (Volta, Turing, and NVIDIA Ampere GPU architecture) for development purposes.
            Care must be taken to not exceed the memory available when selecting models to deploy.*

    * - Mic, Camera, and Headset
      - 
        **Microphone**:

            - Linux x86 with USB microphone 
              (for example, a Logitech H390 USB Computer Headset) 
        
        **Headphones**:

            - Logitech H340
            - Logitech H390
            - Microsoft LX3000

    * - GPU Memory
      - 
            - **ASR Models**

                - Streaming Models: ~5600 MB
                - Non-streaming models: ~3100 MB

            - **NLP Models**

                - ~500MB per BERT model

            - **TTS Models**

                - ~3500 MB

            - **Total**

                - 16000 MB

Software
^^^^^^^^

The following table shows the supported software for Jarvis Speech Skills 1.0.0 Beta.

.. +------------------+----------------------------------------------------+
.. |                  | **Software Compatibility**                         |
.. +------------------+----------------------------------------------------+
.. | CUDA             | *. 11.1                                            |
.. +------------------+----------------------------------------------------+

.. raw:: html
    <style>
      .wy-table-responsive table th {
        white-space: normal;
      }
    </style>

.. list-table:: 
    :header-rows: 1
    :widths: 20 80

    * - 
      - Software Compatibility
    * - CUDA
      - 
            - `10.2 <https://developer.nvidia.com/cuda-toolkit-archive>`_

    * - Docker
      - 
            - Docker > 19.02 with  `nvidia-docker installed <https://github.com/NVIDIA/nvidia-docker>`_
            - For users other than DGX, Docker >= 19.03 is required.

            *Note: For DGX users, see `Preparing to use NVIDIA Containers <http://docs.nvidia.com/deeplearning/frameworks/preparing-containers/index.html>`_.

    * - Helm
      -
            - `Helm charts 3.x <https://ngc.nvidia.com/helm-charts>`_
        
    * - NVIDIA Driver
      - 
            - `440.44+ <https://www.nvidia.com/Download/index.aspx?lang=en-us>`_

            *Note: For earlier driver versions, refer to the NVIDIA Driver section in `Deep Learning Frameworks Support Matrix <https://docs.nvidia.com/deeplearning/frameworks/support-matrix/index.html>`_.