support qwen25 vl w8a8 quantization (#2778)

### What this PR does / why we need it?
support qwen25 vl w8a8 quantization
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?

- vLLM version: v0.10.1.1
- vLLM main:
62f66be1f7

---------

Signed-off-by: lijiaojiao <lijiaojiao990304@163.com>
Co-authored-by: lijiaojiao <lijiaojiao990304@163.com>

vllm_ascend/quantization/quant_config.py

@@ -53,6 +53,7 @@ class AscendQuantConfig(QuantizationConfig):
     """
 
     def __init__(self, quant_config: Dict[str, Any]):
+        super().__init__()
         self.quant_description = quant_config
 
     def __repr__(self) -> str:
@@ -89,6 +90,8 @@ class AscendQuantConfig(QuantizationConfig):
     def get_quant_method(self, layer: torch.nn.Module,
                          prefix: str) -> Optional["QuantizeMethodBase"]:
         from vllm.attention.layer import Attention
+        if prefix.startswith("language_model"):
+            prefix = prefix.split('.', 1)[-1]
         if isinstance(layer, LinearBase):
             if self.is_layer_skipped_ascend(prefix,
                                             self.packed_modules_mapping):