Best practices for reporting an issue or bug relating to TensorRT

This area is to discuss how to best use TensorRT - and discuss problems and issues should they arise.
When reporting a potential bug or issue it really helps our engineers to get a comprehensive understand of the environment and steps to reproduce the problem. This information will enable us to respond faster,

TensorRT developers respond to issues. We want to focus on fixing bugs and adding features.

1) Provide details on the platforms you are using:

  • Linux distro and version
  • GPU type
  • Nvidia driver version
  • CUDA version
  • CUDNN version
  • Python version [if using python]
  • Tensorflow version
  • TensorRT version
    If Jetson, also include OS, hw versions

2) Describe the issue


3) Provide supporting code or data files


4) Reproducibility

  • Please provide a minimal test case that reproduces your error.