Deepstream with standalone triton server

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 5.1
• JetPack Version (valid for Jetson only) 4.5.1
• TensorRT Version 7.2.3
• NVIDIA GPU Driver Version (valid for GPU only) 360.32.03
• Issue Type( questions, new requirements, bugs) Questions
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

Hello,

I need to know, is using DeepStream with standalone triton supported? I want to use single triton server for all my pipelines. Can you please share some reference example do so?
I want to build my pipeline like this.

camera → uridecodebin → streammux → Triton client → triton server (External) —> Triton client (Meta Data) → nvosd → RTSP server

I have tried with nvinferserver and able to run nvinferserver plugin in DeepStream pipeline but I want to run multiple camera or same camera for different analytics use case on same system. I heard that using standalone triton server would be optimised way and can levarage triton server capabilities.

what is your suggestion?

3

Sorry for the late response, is this still an issue to support? Thanks

4

Yes, if you can guide me would be great help. Thanks for your response.

5

nvinferserver is the only way to integrate triton with deepstream. Gst-nvinferserver — DeepStream 6.1.1 Release documentation

8

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.