❓ [Question] What is the difference between docker built on PyTorch NGC Container and PyTorch NGC Container?

[Guangyun-Xu]

❓ Question

Since PyTorch NGC 21.11+ already includes Torch-TensorRT, is it possible to use Torch-TensorRT directly in PyTorch NGC Container?

What you have already tried

I read the README and tried to build docker according to it, but it keeps failing.

Environment

Build information about Torch-TensorRT can be found by turning on debug messages

• PyTorch Version (e.g., 1.0):Do I need to install PyTorch locally?
• CPU Architecture:AMD64/x64
• OS (e.g., Linux):Linux
• How you installed PyTorch (conda, pip, libtorch, source)：not installed
• Build command you used (if compiling from source):
• Are you using local sources or building from archives:
• Python version:
• CUDA version:
• GPU models and configuration:
• Any other relevant information:

Additional context

[narendasan]

Yes you can use the precompiled torch-tensorrt inside the container