Refactor checks for quantization methods

[ckadner]

We'll have to refactor all these checks once we support more quantization methods, today we only support fp8. I wouldn't mind a refactor to at least pull all of these fp8 checks into one helper instance method in the model class, but we don't need to block this fix on it

I do think this is a separate problem than figuring out which model we're serving though, because any fp8 model has to be handled separately here, not just granite specifically.

Originally posted by @joerunde in #535 (comment)

There is some more code to do this kind of check, which could be adapted and used here:

• vllm-spyre/vllm_spyre/platform.py

  Line 597 in de0e3d2

  def is_granite_3_8b(cls, model_config: ModelConfig):

• vllm-spyre/vllm_spyre/config/runtime_config_validator.py

  Line 139 in de0e3d2

  def find_known_models_by_model_config(model_config: ModelConfig) -> list[str]: