Fix formatting

vllm-project · Aug 30, 2024 · 6b9ac06 · 6b9ac06
1 parent 2abdbe1
commit 6b9ac06
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 4 deletions.
diff --git a/vllm/model_executor/layers/quantization/__init__.py b/vllm/model_executor/layers/quantization/__init__.py
@@ -24,7 +24,6 @@
 from vllm.model_executor.layers.quantization.marlin import MarlinConfig
 from vllm.model_executor.layers.quantization.modelopt import ModelOptFp8Config
 from vllm.model_executor.layers.quantization.qqq import QQQConfig
-from vllm.model_executor.layers.quantization.modelopt import ModelOptFp8Config
 from vllm.model_executor.layers.quantization.squeezellm import SqueezeLLMConfig
 from vllm.model_executor.layers.quantization.tpu_int8 import Int8TpuConfig
 

diff --git a/vllm/model_executor/layers/quantization/modelopt.py b/vllm/model_executor/layers/quantization/modelopt.py
@@ -11,8 +11,8 @@
     QuantizationConfig, QuantizeMethodBase)
 from vllm.model_executor.layers.quantization.kv_cache import BaseKVCacheMethod
 from vllm.model_executor.layers.quantization.utils.w8a8_utils import (
-    apply_fp8_linear, cutlass_fp8_supported, requantize_with_max_scale,
-    create_per_tensor_scale_param)
+    apply_fp8_linear, create_per_tensor_scale_param, cutlass_fp8_supported,
+    requantize_with_max_scale)
 from vllm.model_executor.utils import set_weight_attrs
 
 logger = init_logger(__name__)
@@ -65,7 +65,6 @@ def from_config(cls, config: Dict[str, Any]) -> "ModelOptFp8Config":
     def get_quant_method(self, layer: torch.nn.Module,
                          prefix: str) -> Optional["QuantizeMethodBase"]:
         from vllm.attention.layer import Attention  # Avoid circular import
-        from vllm.model_executor.layers.quantization.fp8 import Fp8KVCacheMethod  # Avoid circular import
         if isinstance(layer, LinearBase):
             return ModelOptFp8LinearMethod(self)
         elif isinstance(layer, Attention):