[Feature] Support QuaRot quantization scheme

[serser]

Motivation

QuaRot is out https://arxiv.org/abs/2404.00456 for three weeks. Preliminary results are convincing. Also see discussions in llama.cpp with the QuaRot authors. It would be amazing to have it supported in LMDeploy as default.

Best.

Related resources

https://github.com/ggerganov/llama.cpp/issues/6444 https://arxiv.org/abs/2404.00456

Additional context

No response

[lvhan028]

@pppppM @AllentDan @lzhangzz may investigate QuaRot quantization algorithm, very promising