diff --git a/torch_npu/csrc/aten/common/ToKernelNpu.cpp b/torch_npu/csrc/aten/common/ToKernelNpu.cpp
index 07da82019af8605d0a5d102059433a754a10a871..3e0fabb70931d6516a0a3d73b5cdc5b613c64fac 100644
--- a/torch_npu/csrc/aten/common/ToKernelNpu.cpp
+++ b/torch_npu/csrc/aten/common/ToKernelNpu.cpp
@@ -136,7 +136,7 @@ at::Tensor NPUNativeFunctions::to(
   if (at::ScalarType::Double == dtype) {
     static auto warn_once = []() {
         std::cout << "Warning: Device do not support double dtype now, " \
-                     "dtype cast repalce with float." << std::endl;
+                     "dtype cast replace with float." << std::endl;
         return true;
     }();
   }