diff --git a/vllm/model_executor/models/qwen2.py b/vllm/model_executor/models/qwen2.py
index 01745b5fd53e1..d20fb150f7e39 100644
--- a/vllm/model_executor/models/qwen2.py
+++ b/vllm/model_executor/models/qwen2.py
@@ -298,7 +298,7 @@ def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
             lambda prefix: Qwen2DecoderLayer(config=config,
                                              cache_config=cache_config,
                                              quant_config=quant_config,
-                                             prefix=f"{prefix}.layers"),
+                                             prefix=prefix),
             prefix=f"{prefix}.layers",
         )