[Feature] Will multi-modal models support W8A8 quantization in the future?

### Motivation

Our business model (Internvl 2-26B) outputs very few tokens (1-2 tokens) after prompt optimization, which can be considered as only the prefill stage. Therefore, we hope to use W8A8 quantization to speed up the inference process. However, we found that lmdeploy does not support W8A8 inference for multi-modal models: [https://github.com/InternLM/lmdeploy/issues/2042.](https://github.com/InternLM/lmdeploy/issues/2042.)

Could you please explain why W8A8 quantization is not supported for multi-modal models? Is it due to model accuracy concerns?

### Related resources

_No response_

### Additional context

_No response_