Running Nvidia VST(Video Storage Toolkit) on Mac M1

Accelerated Computing Intelligent Video Analytics Metropolis Microservices for Jetson
1

I am trying to run Nvidia VST on Mac M1 machine.
I downloaded the below docker image

nvcr.io/nvidia/jps/vst:v1.2.58_aarch64

Am trying to run it usind docker run .
My objective is just to run the VST container and see the UI.

However when i run i am not able to see the UI.
The final logs show as:
[2024-7-16T7:9:22.587Z:281473415696416:sensor_management.cpp:633: notifyVmsRedinessEvent] {
“alert_type” : “service_status_change”,
“created_at” : “2024-07-16T07:09:22Z”,
“event” :
{
“service_status” : “init_ready”
},
“source” : “vst”
}

Question:

  1. Is it possible to run VST on a non NVIDIA GPU machine?
  2. If the answer to above is yes, what is that i need to do to make it work correctly on my local machine?
  3. Where can i get the vst_configs.json file ?
  4. What are the minimum fields i need to modify, is there any link which can guide in modifying those fields and giving a brief description of the fields?
2

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
• Ubuntu Version
• 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)

This forum is for JPS on Jetson. I can more the topic to other forum if you can provide more details of your setup.

3

Thanks for the prompt reply.

I am trying to run NVIDIA VST (Video storgae toolkit) – Overview — mms-docs 2.1 documentation

Hardware platform : Apple Mac M1
Ubuntu version : Not applicable
JetPack Version : Not applicable
TensorRT Version : Not applicable
NVIDIA GPU Driver Version (valid for GPU only) : Not applicable
Issue Type( questions, new requirements, bugs) : Question
Reproduce the issue :

  1. Pull the docker image : docker pull nvcr.io/nvidia/jps/vst:v1.2.58_aarch64
  2. Run the image : docker run --rm -it nvcr.io/nvidia/jps/vst:v1.2.58_aarch64
    Expectation : Web UI launched on a URL
    Observation : Not able to open the UI

Not sure where this question fits exactly, any help would be appreciated

4

VST depend on NVIDIA GPU for video decode/encode and video process (draw line onto video). I think we only test it on NVIDIA dGPU or Jetson.

5

Thanks, understood.

If i run it on a remove server which has gpu, can i access the UI from a different machine, if yes, what is the process for that.

E,g,

  1. VST running on a machine with ip a.b.c
  2. Access the web UI from a different machine with x.y.z
    How to do it?
6

You can access VST with Chrome browser. If the server and client in different network, you need install TURN based on: Usage & Configuration — mms-docs 2.1 documentation (nvidia.com)

7

My VST container is running on a remote server which does not have a UI component.
I am trying to access the VST web UI from a different machine. Do i need to install the TURN on the server?

One more question:
I found 2 different images
nvcr.io/nvidia/jps/vst:nvstreamer_v0.2.31_x86_64
nvcr.io/rxczgrvsg8nx/vst-1-0/vst:v1.2.60_x86_64
Which is the one which has to be used

8

Any update on this?

9

Seems VST works in your side based on. Please try to use the latest version of VST: Recording in VST(Video storage toolkit) - #8 by rahul.jha

10

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

11

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