[BugFix]add int8 cache dtype when using attention quantization

[Angazenn]

1. Ascend attention requires int8 kvcache dtype. It is used in initialization of CacheConfig:

if cache_config.cache_dtype == "auto":
    self.dtype = model_config.dtype
else:
    self.dtype = STR_DTYPE_TO_TORCH_DTYPE[cache_config.cache_dtype]

STR_DTYPE_TO_TORCH_DTYPE is defined in vllm.utils:

STR_DTYPE_TO_TORCH_DTYPE = {
    "half": torch.half,
    "bfloat16": torch.bfloat16,
    "float": torch.float,
    "fp8": torch.uint8,
    "fp8_e4m3": torch.uint8,
    "fp8_e5m2": torch.uint8,
}

Hence we need to update both cache_dtype and STR_DTYPE_TO_TORCH_DTYPE.

[whx-sjtu]

Does vllm originally has entrypoints to resgister custom quant types into STR_DTYPE_TO_TORCH_DTYPE? If not, maybe we need to make this an issue to vllm? @wangxiyuan please check this.

[wangxiyuan]

No, we can create a pr to vllm later.

Currenlty. for this kind of change(Monkey patch), please move it to the patch module.

[MengqingCao]

CI failed due to the test path update in vLLM, will fix in #124

[wangxiyuan]

I think this PR need a rebase