[Feature]: AutoDeploy: support HF-native fp8 dynamic quantization

[lucaslie]

🚀 The feature, motivation and pitch

Minimax checkpoint uses dynamic fp8 quantization using the HF-native format, see https://huggingface.co/MiniMaxAI/MiniMax-M2/blob/main/config.json#L96-L109.

Let's add support for this in our quantization sources. see https://nvidia.slack.com/archives/C08T55LHSG4/p1767814621927509

Alternatives

No response

Additional context

No response

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.