How to keep DeepStream pipeline in running status without feeding any input

Hello everyone,
I was wondering if there is a way of keeping deepstream pipeline in the running state, even after the end of the session? so that for the next session we don’t need to undergo the latency of loading the weights, engines etc. If this is possible would you point me to the code that I need to modify for this purpose?


• Hardware Platform (Jetson / GPU)
• DeepStream Version deepstream sdk 5.0
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
NVIDIA-SMI 465.19.01 Driver Version: 465.19.01 CUDA Version: 11.3
• 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)

I think you can don’t choose to call g_main_loop_quit when recieve EOS of the stream. you can refer The Main Event Loop: GLib Reference Manual

Thanks a lot for your reply. Which .c file do I have to look into to make these sorts of changes?


I think maybe you can start with a simple sample like deepstream-test1 to verify it.