[Usage]: How to apply pipeline parallelism across multi-nodes with tensorrt-llm container running on each node?

System Info

System Information:

• OS:
• Python version:
• CUDA version:
• GPU model(s):
• Driver version:
• TensorRT-LLM version: 1.2.0rc1

Detailed output:

Paste the output of the above commands here

How would you like to use TensorRT-LLM

I want to run distributed inference on multi-nodes, each node has single GPU, the only releated document/description I can found is https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/disaggregated/README.md but the procedures are not very clear. How can I setup Slurm cluster across docker containers and run pipeline parallelism?

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.