[Usage]: Which workflow will be support for tensorrt-LLM? The engine build path or the PyTorch backend/trtllm-serve?

System Info

System Information:

• OS:
• Python version:
• CUDA version:
• GPU model(s):
• Driver version:
• TensorRT-LLM version:

Detailed output:

Paste the output of the above commands here

How would you like to use TensorRT-LLM

It isn’t very obvious whether the previous engine build path where going checkpoint -> trtllm build is still the proper path for utilizing tensorrt LLM, or if the PyTorch backend is the new way to run this container.

Want to make sure I align with the setup that will have long term support for new models and upgrades.
Thanks.

Before submitting a new issue...

• Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.