[error] when DeepsTream`s container using Triton Inference Server through gRPC,Segmentation fault (core dumped)

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU) T4
**• DeepStream Version 6.0
• JetPack Version (valid for Jetson only)
• TensorRT Version
**• NVIDIA GPU Driver Version (valid for GPU only) 440.33.01
**• Issue Type( questions, new requirements, bugs) 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’m using Python API.When I run the program in DeepStream’s Triton Inference Server container.Its ok.But when I run it in DeepsTreams container using Triton Inference Server through gRPC, I met this error.The Triton Inference Server version is 21.08, the same as DeepStream’s Triton Inference Server container.
the error PRINT is:

Starting pipeline 

INFO: infer_grpc_backend.cpp:164 TritonGrpcBackend id:1 initialized for model: yolov5onnx
Segmentation fault (core dumped)

It is the triton model folder：
triton_model.zip (54.1 MB)

this is the code:
deepstream_yolov5.py (11.3 KB)

this is the config file:
dsyolov5_nopostprocess_grpc.txt (663 Bytes)

this is the label file:
labels.txt (624 Bytes)

3

Sorry for the late response, have you managed to get issue resolved or still need the support? Thanks

4

I still need the support.It still shows the problem.
I don’t know what’s wrong and how to avoid it next time.

5

Sorry!
DeepStream’s Triton Inference Server container is “nvcr.io/nvidia/deepstream:6.0-triton” right?
What is “DeepsTream` s container using Triton Inference Server”?

7

yes, DeepStream’s Triton Inference Server container is “nvcr.io/nvidia/deepstream:6.0-triton”

8

can you check both questions?

9

DeepsTream` s container using Triton Inference Server refer to Gst-nvinferserver — DeepStream 6.1.1 Release documentation.
DeepStream container is nvcr.io/nvidia/deepstream:6.0-triton.
Triton Inference Server is nvcr.io/nvidia/tritonserver:21.08-py3

10

nvcr.io/nvidia/deepstream:6.0-triton already supports gRPC, can you just use nvcr.io/nvidia/deepstream:6.0-triton instead of Triton server docker?

11

What I need is one machine install deepstream used to video decode and another machine install triton used to inference

12

In addition to supporting native inference, DeepStream applications can communicate with independent/remote instances of Triton Inference Server using gRPC, allowing the implementation of distributed inference solutions.

13

Here is A machine installed deepstream which is used to video decode,B machine installed triton which is used to inference.A machine communicate with B machine using gRPC.
How to use nvcr.io/nvidia/deepstream:6.0-triton instead of Triton server docker in B machine?

14

README (6.9 KB)
samples/configs/deepstream-app-triton-grpc/README
I think you should read it carefully.