[BugFix] Fix bugs when using ascend quantization (#275)

### What this PR does / why we need it?
It fixes following bugs:
1. When searching a specific linear quantization implementation from a
tool (such as MindIE-Turbo), the mapping of packed linear is required to
identify correponding quant type.
2. The exception is narrowed down to ImportError when importing
MindIETurboQuantizer to better throw other errors.
3. The api of AscendKVCacheMethod.apply is aligned with that in
AscendAttentionBackendImpl.

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
By performing offline inference:

![image](https://github.com/user-attachments/assets/d63804cf-c060-451f-9cb0-d012e06b5333)

---------

Signed-off-by: angazenn <zengyanjia@huawei.com>
Co-authored-by: angazenn <zengyanjia@huawei.com>

vllm_ascend/quantization/quantizer.py

@@ -16,7 +16,7 @@
 #
 
 import importlib
-from typing import Any, Dict, List
+from typing import Any, Dict, List, Optional
 
 CUSTOMIZED_QUANTIZER_TYPE: List[str] = []
 
@@ -25,7 +25,11 @@ class AscendQuantizer:
     """An interface to different quantization implementations for ascend hardwares."""
 
     @classmethod
-    def get_quantizer(cls, quant_config: Dict[str, Any], prefix: str):
+    def get_quantizer(cls,
+                      quant_config: Dict[str, Any],
+                      prefix: str,
+                      packed_modules_mapping: Optional[Dict[str,
+                                                            Any]] = dict()):
         # TODO: Need a param to choose quantization algorithms.
         quantization_algorithm = ''
 
@@ -35,11 +39,12 @@ class AscendQuantizer:
         try:
             module = importlib.import_module("mindie_turbo")
             MindIETurboQuantizer = module.MindIETurboQuantizer
-        except Exception:
+        except ImportError:
             raise NotImplementedError(
                 "There is no available ascend quantizer.")
 
-        return MindIETurboQuantizer.get_quantizer(quant_config, prefix)
+        return MindIETurboQuantizer.get_quantizer(quant_config, prefix,
+                                                  packed_modules_mapping)
 
     def build_linear_method(self):
         raise NotImplementedError