Integration of TurboMind AWQ (#2828)

Co-authored-by: root <bjmsong@126.com>

python/sglang/srt/layers/quantization/__init__.py

@@ -20,6 +20,7 @@ from vllm.model_executor.layers.quantization.marlin import MarlinConfig
 from vllm.model_executor.layers.quantization.qqq import QQQConfig
 from vllm.model_executor.layers.quantization.tpu_int8 import Int8TpuConfig
 
+from sglang.srt.layers.quantization.awq_turbomind import AWQTurbomindConfig
 from sglang.srt.layers.quantization.base_config import QuantizationConfig
 from sglang.srt.layers.quantization.fp8 import Fp8Config
 from sglang.srt.layers.quantization.modelopt_quant import ModelOptFp8Config
@@ -37,6 +38,7 @@ QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
     "gptq_marlin_24": GPTQMarlin24Config,
     "gptq_marlin": GPTQMarlinConfig,
     "awq_marlin": AWQMarlinConfig,
+    "awq_turbomind": AWQTurbomindConfig,
     "gptq": GPTQConfig,
     "compressed-tensors": CompressedTensorsConfig,
     "bitsandbytes": BitsAndBytesConfig,