[Usage]: Request for Detailed Configuration

[Playerrrrr]

Your current environment

The output of `python collect_env.py`

How would you like to use vllm

I want to run inference of a Qwen 2.5 instruct 72b. I don't know whats the most optimal config command is to run it with. Given my hardware config of 4xA100's.

Motivation:
Seeing the MI300X detailed config command from the blogpost, made me wonder what is the one for A100 at the current latest version of VLLM?

https://blog.vllm.ai/2024/10/23/vllm-serving-amd.html

Before submitting a new issue...

• Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.