What is the maximum number of serial models supported by nvinfer?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

For model inference, I have 5 master engine models and I want to perform serial inference. I want to know the maximum number of serial models supported by nvinfer.

  • deepstream-app version 6.1.0
  • DeepStreamSDK 6.1.0
  • CUDA Driver Version: 11.4
  • CUDA Runtime Version: 11.0
  • TensorRT Version: 8.2
  • cuDNN Version: 8.4
  • libNVWarp360 Version: 2.0.1d3
    device on : jetson orin
3

Which do you mean， run mutilple models with one nvinfer or running multiple nvifers at the same time？

4

running multiple nvifers at the same time.

5

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one.
Thanks
It depends on the memory size, codec capability , etc… of your device.

7

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