The platform DeepStream Version 6.2 running on Xavier AGX running JetPack 5.1. I’m building a parallel inference pipeline in Python basing it on your C++ example. I was wonder whether the inference engine include with DeepStream can run parallel inferencing or do I have install and build the C++ example (GitHub - NVIDIA-AI-IOT/deepstream_parallel_inference_app: A project demonstrating how to use nvmetamux to run multiple models in parallel.) . It is unclear to me.
Thank you for your help
Steve
What do you mean by this?
It is TensorRT who load and build the models. The DeepStream SDK is just a framework. It has nothing to do with which programmin language you use.
My apologies for being unclear, and I guess I was really asking this question.
Does DeepSteam 6.2 natively support parallel inferencing?
Thank you for your help
Steve
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
Yes. NVIDIA-AI-IOT/deepstream_parallel_inference_app: A project demonstrating how to use nvmetamux to run multiple models in parallel. (github.com) can work on DeepStream 6.2.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.