Triton with python-binding

[mmoroclash]

• Hardware Platform (Jetson / GPU). Jetson Nano
• DeepStream Version 6.0.1
• JetPack Version (valid for Jetson only) 4.6.3
• TensorRT Version 8.2.1.8
• NVIDIA GPU Driver Version (valid for GPU only). CUDA: 10.2.300
• Issue Type( questions)

I’m trying to install triton inside nvcr.io/nvidia/dli/dli-nano-deepstream:v2.0.0-DS6.0.1,
I followed both the main doc (here)[server/jetson.md at main · triton-inference-server/server · GitHub]
and this script too /opt/nvidia/deepstream/deepstream/samples/triton_backend_setup.sh
but i got those when reach the command “ldconfig”

and “gst-inspect-1.0 nvinferserver” return no nvinferserver found, and the ElementFactory can’t carate nvinferserver, how i can solve this issue, I want to run DeepStream along side with triton.

and deepstream-l4t–6.0.1-trition not has python-binding, also gst-inspect-1.0 nvinferserver return nothing.

[yingliu]

Does this topic has the same goal of installation python on deepstream-triton on nano? Starting from docker should be more straightforward, we can focus on that topic.
Install python binding in deepstream-l4t-6.0.1-triton - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums?

[mmoroclash]

I’m trying to fix it long hours ago, and that is one of the trials.

[yingliu]

OK, let’s focus on this one: Install python binding in deepstream-l4t-6.0.1-triton - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums