[0.9.1]disable quantization in mindie_turbo (#1749)

### What this PR does / why we need it?
since the interface in vllm-ascend has changed so quickly, the
quantization function in mindie_turbo is no longer needed, so it needs
to be discarded.

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

### How was this patch tested?
through ci

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

Author: zouyida2052

vllm_ascend/quantization/quantizer.py

@@ -48,14 +48,8 @@ def get_quantizer(cls,
         if quantization_algorithm in CUSTOMIZED_QUANTIZER_TYPE:
             return
 
-        try:
-            module = importlib.import_module("mindie_turbo")
-            MindIETurboQuantizer = module.MindIETurboQuantizer
-            return MindIETurboQuantizer.get_quantizer(quant_config, prefix,
-                                                      packed_modules_mapping)
-        except ImportError:
-            return VLLMAscendQuantizer.get_quantizer(quant_config, prefix,
-                                                     packed_modules_mapping)
+        return VLLMAscendQuantizer.get_quantizer(quant_config, prefix,
+                                                 packed_modules_mapping)
 
     def build_linear_method(self):
         raise NotImplementedError