diff --git a/vllm/config/compilation.py b/vllm/config/compilation.py
index 1c3ef502f0f45..abdae49106120 100644
--- a/vllm/config/compilation.py
+++ b/vllm/config/compilation.py
@@ -664,6 +664,8 @@ class CompilationConfig:
             is_torch_equal_or_newer("2.9.0.dev")
             and "combo_kernels" not in self.inductor_compile_config
             and "benchmark_combo_kernel" not in self.inductor_compile_config
+            # (fixme @boyuan) combo kernel does not support cpu yet.
+            and not current_platform.is_cpu()
         ):
             # use horizontal fusion, which is useful for fusing qk-norm and
             # qk-rope when query and key have different shapes.