============= Compute Setup ============= x86 Platforms ------------- 1. Prepare a NVIDIA-powered platform with the following minimum specs: - Ubuntu 22.04+ - **Experimental**: WSL2 on Windows 11 - 16 GB general RAM - Discrete NVIDIA GPU with the following specs: - supports CUDA 12.6+ with ``Ampere`` NVIDIA GPU Architecture or newer - minimum 8GB of VRAM and recommended 12GB+ .. note:: Various DNN models when loaded together can consume more memory than you may have available. 2. Install Docker from official instructions (`here `__). (Recommended 27.2.0 or newer) 3. Install the latest NVIDIA GPU Driver from official instructions (`here `__). (Minimum 560+ is required, see `here `__). Jetson Platforms ---------------- 1. `Install Jetpack `__ including the ``nvidia-container`` package. 2. After boot, confirm that you have installed the correct version of ``Jetpack`` by running the following command. Confirm that the output has the terms ``R36 (release), REVISION: 4.0``. .. code:: bash cat /etc/nv_tegra_release 3. Run the following command to set the GPU and CPU clock to max. See `Maximizing Jetson Performance `__ for more details. .. code:: bash sudo /usr/bin/jetson_clocks 4. Run the following command to set the to power to MAX settings. See `Power Mode Controls `__ for more details. .. code:: bash sudo /usr/sbin/nvpmodel -m 0 5. Add your user to the ``docker`` group. .. code:: bash sudo usermod -aG docker $USER newgrp docker 6. Setup Docker. .. include:: /_snippets/docker_buildx.rst Consider adding more storage to your Jetson for a better experience: :doc:`Developer Environment Setup for Jetson ` .. toctree:: :hidden: :maxdepth: 1 jetson_storage.rst preempt_setup.rst jetson_vpi.rst