Add RoPE scaling arguments to engine

[AlpinDale]

Currently, we auto-scale using the --max-model-len argument. It may be more appropriate to have specific options for the scaling factor, etc.

[jagilley]

There are some models for long context tasks like storywriting that it'd be nice to use with a static RoPE scaling factor. +1 on this!

[sparsh35]

Hi getting error for bigger context models like Microsoft Phi 3 medium with respect to rope scaling factors with exl2 format.

[sparsh35]

It is something related to this I think, maybe not much needs to be done here, just implement this code , I will try to test if it doesn't breaks anything else , here is the git in vllm for this feature vllm-project/vllm#4638

[sparsh35]

vllm-project/vllm#4298 vllm has implemented rotatry scale embeddings like this