Apply sgl w8a8 fp8 kernel (#3148)

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

@@ -28,6 +28,7 @@ from sglang.srt.layers.quantization.blockwise_int8 import BlockInt8Config
 from sglang.srt.layers.quantization.fp8 import Fp8Config
 from sglang.srt.layers.quantization.gptq import GPTQConfig, GPTQMarlinConfig
 from sglang.srt.layers.quantization.modelopt_quant import ModelOptFp8Config
+from sglang.srt.layers.quantization.w8a8_fp8 import W8A8Fp8Config
 from sglang.srt.layers.quantization.w8a8_int8 import W8A8Int8Config
 
 QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
@@ -50,6 +51,7 @@ QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
     "qqq": QQQConfig,
     "experts_int8": ExpertsInt8Config,
     "w8a8_int8": W8A8Int8Config,
+    "w8a8_fp8": W8A8Fp8Config,
 }