[2/2] Support Qserve (#6521)

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

@@ -67,6 +67,7 @@ from sglang.srt.layers.quantization.modelopt_quant import (
     ModelOptFp8Config,
 )
 from sglang.srt.layers.quantization.moe_wna16 import MoeWNA16Config
+from sglang.srt.layers.quantization.qoq import QoQConfig
 from sglang.srt.layers.quantization.w8a8_fp8 import W8A8Fp8Config
 from sglang.srt.layers.quantization.w8a8_int8 import W8A8Int8Config
 
@@ -80,6 +81,7 @@ BASE_QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
     "w8a8_fp8": W8A8Fp8Config,
     "moe_wna16": MoeWNA16Config,
     "compressed-tensors": CompressedTensorsConfig,
+    "qoq": QoQConfig,
 }
 
 # VLLM-dependent quantization methods