[Kernel] Marlin Expansion: Support AutoGPTQ Models with Marlin (#3922)

Co-authored-by: alexm <alexm@neuralmagic.com>
Co-authored-by: mgoin <michael@neuralmagic.com>

vllm/model_executor/layers/quantization/__init__.py

@@ -6,6 +6,8 @@ from vllm.model_executor.layers.quantization.base_config import (
     QuantizationConfig)
 from vllm.model_executor.layers.quantization.fp8 import Fp8Config
 from vllm.model_executor.layers.quantization.gptq import GPTQConfig
+from vllm.model_executor.layers.quantization.gptq_marlin import (
+    GPTQMarlinConfig)
 from vllm.model_executor.layers.quantization.marlin import MarlinConfig
 from vllm.model_executor.layers.quantization.squeezellm import SqueezeLLMConfig
 
@@ -15,6 +17,7 @@ QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
     "fp8": Fp8Config,
     "gptq": GPTQConfig,
     "squeezellm": SqueezeLLMConfig,
+    "gptq_marlin": GPTQMarlinConfig,
     "marlin": MarlinConfig,
 }