Revert "[Feature][Quant] Auto-detect quantization format from model f… (#6873)

This reverts commit 3953dcf784. to keep
the basic functions available

---------

Signed-off-by: wangli <wangli858794774@gmail.com>

vllm_ascend/platform.py

@@ -178,11 +178,6 @@ class NPUPlatform(Platform):
 
     @classmethod
     def check_and_update_config(cls, vllm_config: VllmConfig) -> None:
-        from vllm_ascend.quantization.utils import maybe_auto_detect_quantization
-
-        if vllm_config.model_config is not None:
-            maybe_auto_detect_quantization(vllm_config)
-
         # initialize ascend config from vllm additional_config
         cls._fix_incompatible_config(vllm_config)
         ascend_config = init_ascend_config(vllm_config)