Move FP8 to SGLang (#2370)

Co-authored-by: HaiShaw <[email protected]>

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

@@ -13,7 +13,6 @@
 from vllm.model_executor.layers.quantization.deepspeedfp import DeepSpeedFPConfig
 from vllm.model_executor.layers.quantization.experts_int8 import ExpertsInt8Config
 from vllm.model_executor.layers.quantization.fbgemm_fp8 import FBGEMMFp8Config
-from vllm.model_executor.layers.quantization.fp8 import Fp8Config, Fp8MoEMethod
 from vllm.model_executor.layers.quantization.gguf import GGUFConfig
 from vllm.model_executor.layers.quantization.gptq import GPTQConfig
 from vllm.model_executor.layers.quantization.gptq_marlin import GPTQMarlinConfig
@@ -23,6 +22,7 @@
 from vllm.model_executor.layers.quantization.tpu_int8 import Int8TpuConfig
 
 from sglang.srt.layers.quantization.base_config import QuantizationConfig
+from sglang.srt.layers.quantization.fp8 import Fp8Config, Fp8MoEMethod
 
 QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
     "aqlm": AQLMConfig,
@@ -100,13 +100,13 @@ def fp8_moe_apply(
 def fp8_get_quant_method(self, layer, prefix):
     """Enhanced get_quant_method for FP8 config."""
     from vllm.model_executor.layers.linear import LinearBase
-    from vllm.model_executor.layers.quantization.fp8 import Fp8LinearMethod
     from vllm.model_executor.layers.quantization.utils.quant_utils import (
         is_layer_skipped,
     )
 
     from sglang.srt.layers.fused_moe_triton.layer import FusedMoE
     from sglang.srt.layers.linear import UnquantizedLinearMethod
+    from sglang.srt.layers.quantization.fp8 import Fp8LinearMethod
 
     if isinstance(layer, LinearBase):
         if is_layer_skipped(prefix, self.ignored_layers):