Integrate Marlin Kernels for Int4 GPTQ inference (#2497)

Co-authored-by: Robert Shaw <114415538+rib-2@users.noreply.github.com>
Co-authored-by: alexm <alexm@neuralmagic.com>

vllm/model_executor/layers/quantization/__init__.py

@@ -4,11 +4,13 @@ from vllm.model_executor.layers.quantization.base_config import QuantizationConf
 from vllm.model_executor.layers.quantization.awq import AWQConfig
 from vllm.model_executor.layers.quantization.gptq import GPTQConfig
 from vllm.model_executor.layers.quantization.squeezellm import SqueezeLLMConfig
+from vllm.model_executor.layers.quantization.marlin import MarlinConfig
 
 _QUANTIZATION_CONFIG_REGISTRY = {
     "awq": AWQConfig,
     "gptq": GPTQConfig,
     "squeezellm": SqueezeLLMConfig,
+    "marlin": MarlinConfig,
 }