AGX Orin DevKit (Concord w/Jango SKU5) - T234

AGX Orin 32/64GB (Jango SKU4/5) - T234

Orin NX 16/8GB (Grogu SKU0/1) - T234

Orin Nano DevKit (Arvala w/Grogu SKU3) - T234

Orin Nano 8/4GB (Grogu SKU3/4) - T234

AGX Xavier 16/32/64 / XNX 8/16 / JAXi- T194

TX2/TX2i/TX2 4GB/NX - T186

Nano 2GB/4GB / TX1 - T210

known limitations

• NVMe driver cannot be in 4Kn mode

command

# refers to /etc/nvpmodel.conf for predefined model
sudo nvpmodel -q

# check UEFI version
sudo nvbootctrl dump-slots-info

## install pytorch

https://docs.nvidia.com/deeplearning/frameworks/install-pytorch-jetson-platform/index.html

https://github.com/dusty-nv/jetson-containers/tree/master

sudo docker run --runtime nvidia -it --rm --network=host $(autotag l4t-pytorch)

sudo docker run --runtime nvidia -it -v /home/nvidia/Wav2Lip /workspace/Wav2Lip --network=host $(./autotag l4t-pytorch)

https://docs.pytorch.org/tutorials/prototype/pt2e_quant_ptq.html

# install jetpack, it seems that the default installtion is skipped due to opencv vesion conflict
sudo apt install nvidia-jetpack

# install pytorch
sudo apt-get install -y  python3-pip libopenblas-dev;

wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/arm64/cuda-keyring_1.1-1_all.deb
sudo dpkg -i cuda-keyring_1.1-1_all.deb
sudo apt-get update
sudo apt-get -y install libcusparselt0 libcusparselt-dev
# this package source also have potentional higher version of cuda than jetpack default
# not sure if that is needed

# https://developer.download.nvidia.com/compute/redist/jp/v$JP_VERSION/pytorch/$PYT_VERSION
# note at the time of writing, no v62 is available
sudo apt-get install virtualenv
python3 -m virtualenv -p python3 <chosen_venv_name>

source <chosen_venv_name>/bin/activate

python3 -m pip install --upgrade pip; 
python3 -m pip install 'numpy<2' # torch was compiled against numpy 1
python3 -m pip install --no-cache $TORCH_INSTALL

https://developer.download.nvidia.com/compute/redist/jp/v61/pytorch/torch-2.5.0a0+872d972e41.nv24.08.17622132-cp310-cp310-linux_aarch64.whl

super mode

https://www.stereolabs.com/blog/getting-started-with-nvidia-orin-nano-super-and-zed

https://developer.nvidia.com/blog/nvidia-jetpack-6-2-brings-super-mode-to-nvidia-jetson-orin-nano-and-jetson-orin-nx-modules/

desgin doc

https://developer.nvidia.com/embedded/community/support-resources

initial setup - more details

https://www.jetson-ai-lab.com/initial_setup_jon_sdkm.html

question: will this be equivalent to the flash tool?

flashing guide

https://docs.nvidia.com/jetson/archives/r36.4/DeveloperGuide/IN/QuickStart.html#

sudo ./tools/kernel_flash/l4t_initrd_flash.sh –external-device nvme0n1p1
-c tools/kernel_flash/flash_l4t_t234_nvme.xml
-p “-c bootloader/generic/cfg/flash_t234_qspi.xml”
–showlogs –network usb0 jetson-orin-nano-devkit internal

jetson-orin-nano-devkit-super.conf??

orange pi

http://www.orangepi.cn/html/hardWare/computerAndMicrocontrollers/service-and-support/Orange-Pi-AIpro(20T).html

http://www.orangepi.cn/html/hardWare/computerAndMicrocontrollers/service-and-support/Orange-Pi-5-Ultra.html