diff --git a/vllm/v1/attention/backends/cpu_attn.py b/vllm/v1/attention/backends/cpu_attn.py
index 511387aac..689109aac 100644
--- a/vllm/v1/attention/backends/cpu_attn.py
+++ b/vllm/v1/attention/backends/cpu_attn.py
@@ -36,10 +36,6 @@ class CPUAttentionBackend(AttentionBackend):
         torch.float32,
     ]
 
-    @classmethod
-    def get_supported_dtypes(cls) -> list[torch.dtype]:
-        return [torch.float16, torch.bfloat16, torch.float32]
-
     @classmethod
     def get_supported_head_sizes(cls) -> list[int]:
         return [32, 64, 80, 96, 112, 128, 160, 192, 224, 256]