Can Deepstream run 1 application across different GPUs

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) H100
• DeepStream Version 7.0
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• 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)

Hi, I would like to ask

  1. Can i use deepstream to run on 2 different GPUs? For example, I would like my decoding, streammux to be done on GPUID 0 and inference to be done on GPUID 1.
  2. Lets say I am decoding 1 stream @25fps and it uses 500MB of VRAM, if I am reading the stream @1fps, will the VRAM drop? Assuming 1fps is set from my camera source, not dropping frames within Deepstream
3
  1. yes. you can set gpu-id property of nvstreammux and nvinfer plugin.
  2. In theory, the VRAM will drop. if using 25pfs, the decoder needs more buffers for reference frames.
4

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.

5

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