[quantization][config] enable override existing quant_config (#28510)

Signed-off-by: Hank <hcc.mayday@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

vllm/model_executor/layers/quantization/__init__.py

@@ -3,8 +3,11 @@
 
 from typing import Literal, get_args
 
+from vllm.logger import init_logger
 from vllm.model_executor.layers.quantization.base_config import QuantizationConfig
 
+logger = init_logger(__name__)
+
 QuantizationMethods = Literal[
     "awq",
     "deepspeedfp",
@@ -70,15 +73,20 @@ def register_quantization_config(quantization: str):
 
     def _wrapper(quant_config_cls):
         if quantization in QUANTIZATION_METHODS:
-            raise ValueError(
-                f"The quantization method `{quantization}` is already exists."
+            logger.warning(
+                "The quantization method '%s' already exists and will be "
+                "overwritten by the quantization config %s.",
+                quantization,
+                quant_config_cls,
             )
+        else:
+            QUANTIZATION_METHODS.append(quantization)
+
         if not issubclass(quant_config_cls, QuantizationConfig):
             raise ValueError(
                 "The quantization config must be a subclass of `QuantizationConfig`."
             )
         _CUSTOMIZED_METHOD_TO_QUANT_CONFIG[quantization] = quant_config_cls
-        QUANTIZATION_METHODS.append(quantization)
         return quant_config_cls
 
     return _wrapper