Feature Request: MiniMax M2 support

[Juste-Leo2]

Prerequisites

• I am running the latest code. Mention the version if possible as well.
• I carefully followed the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• I reviewed the Discussions, and have a new and useful enhancement to share.

Feature Description

Add support for the MiniMax-M2 model.

Motivation

It’s a state-of-the-art (SOTA) model that matches or even outperforms many existing models.

Possible Implementation

https://docs.vllm.ai/projects/recipes/en/latest/MiniMax/MiniMax-M2.html
https://huggingface.co/MiniMaxAI/MiniMax-M2/blob/main/docs/vllm_deploy_guide.md

[BahamutRU]

The most interesting and most important modern model, pls, focus on it. We are really looking forward to it.

[pwilkin]

PR is up.

[Juste-Leo2]

Closing this Issue.

Huge thanks to @pwilkin for the incredible implementation work on MiniMax M2 support! The Pull Request is available here: #16831. 🚀