Feature DeepSeek V3/R1 INT8 Quantization (block-wise) (#3730)

Co-authored-by: HandH1998 <1335248067@qq.com>

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

@@ -24,6 +24,7 @@ from vllm.model_executor.layers.quantization.qqq import QQQConfig
 from vllm.model_executor.layers.quantization.tpu_int8 import Int8TpuConfig
 
 from sglang.srt.layers.quantization.base_config import QuantizationConfig
+from sglang.srt.layers.quantization.blockwise_int8 import BlockInt8Config
 from sglang.srt.layers.quantization.fp8 import Fp8Config
 from sglang.srt.layers.quantization.modelopt_quant import ModelOptFp8Config
 from sglang.srt.layers.quantization.w8a8_int8 import W8A8Int8Config
@@ -34,6 +35,7 @@ QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
     "deepspeedfp": DeepSpeedFPConfig,
     "tpu_int8": Int8TpuConfig,
     "fp8": Fp8Config,
+    "blockwise_int8": BlockInt8Config,
     "fbgemm_fp8": FBGEMMFp8Config,
     "marlin": MarlinConfig,
     "modelopt": ModelOptFp8Config,