diff --git a/vllm/model_executor/models/llama.py b/vllm/model_executor/models/llama.py
index dfd75a60c67a6..2d53017ef9d55 100644
--- a/vllm/model_executor/models/llama.py
+++ b/vllm/model_executor/models/llama.py
@@ -271,15 +271,13 @@ def forward(
 @support_torch_compile
 class LlamaModel(nn.Module):
 
-    def __init__(
-        self,
-        config: LlamaConfig,
-        cache_config: Optional[CacheConfig] = None,
-        quant_config: Optional[QuantizationConfig] = None,
-        lora_config: Optional[LoRAConfig] = None,
-        prefix: str = "",
-        **kwargs
-    ) -> None:
+    def __init__(self,
+                 config: LlamaConfig,
+                 cache_config: Optional[CacheConfig] = None,
+                 quant_config: Optional[QuantizationConfig] = None,
+                 lora_config: Optional[LoRAConfig] = None,
+                 prefix: str = "",
+                 **kwargs) -> None:
         super().__init__()
         self.config = config
         self.padding_idx = config.pad_token_id