Whne ICudaEngine destroies, program segment fault

AI & Data Science Deep Learning (Training & Inference) TensorRT
,
1

Description

std::shared_ptr<nvinfer1::ICudaEngine> parse_planmodel() {
    std::shared_ptr<nvinfer1::ILogger> logger(new Logger());
    std::shared_ptr<nvinfer1::IRuntime> runtime(nvinfer1::createInferRuntime(*logger));
    std::shared_ptr<nvinfer1::ICudaEngine> engine = nullptr;
    std::ifstream planFile(planmodel, std::ios::binary);
    planFile.seekg(0, planFile.end);
    int model_size = planFile.tellg();
    planFile.seekg(0, planFile.beg);
    std::vector<char> serialize_model(model_size);
    planFile.read(serialize_model.data(), model_size);
    engine.reset(runtime->deserializeCudaEngine(serialize_model.data(), model_size));
    if(engine == nullptr){
        std::cout << "deserialization fails" << std::endl;
        exit(1);
    }else{
        std::cout << "deserialization success" << std::endl;
    }
    return engine;
}

int main(void){
    auto engine = parse_planmodel();
    engine->createExecutionContext();
    return 0;
}

A clear and concise description of the bug or issue.
This program will be segment fault at engine destructor in main function. Why?

Environment

TensorRT Version: 8.6.1.6
GPU Type: Tesla P40
Nvidia Driver Version: 535.86.10
CUDA Version: 12.2
CUDNN Version:
Operating System + Version: CentOS 7
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)

Steps To Reproduce

Please include:

  • Exact steps/commands to build your repro
  • Exact steps/commands to run your repro
  • Full traceback of errors encountered