[Hardware][CPU] Support AWQ for CPU backend (#7515)

vllm/model_executor/layers/quantization/__init__.py

@@ -21,6 +21,7 @@ from vllm.model_executor.layers.quantization.gptq_marlin import (
     GPTQMarlinConfig)
 from vllm.model_executor.layers.quantization.gptq_marlin_24 import (
     GPTQMarlin24Config)
+from vllm.model_executor.layers.quantization.ipex_quant import IPEXConfig
 from vllm.model_executor.layers.quantization.marlin import MarlinConfig
 from vllm.model_executor.layers.quantization.modelopt import ModelOptFp8Config
 from vllm.model_executor.layers.quantization.neuron_quant import (
@@ -49,6 +50,7 @@ QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
     "qqq": QQQConfig,
     "experts_int8": ExpertsInt8Config,
     "neuron_quant": NeuronQuantConfig,
+    "ipex": IPEXConfig,
 }