diff --git a/onnxruntime/contrib_ops/cpu/quantization/quant_gemm.cc b/onnxruntime/contrib_ops/cpu/quantization/quant_gemm.cc
index 91aca25ede..2bd8c3ff6b 100644
--- a/onnxruntime/contrib_ops/cpu/quantization/quant_gemm.cc
+++ b/onnxruntime/contrib_ops/cpu/quantization/quant_gemm.cc
@@ -5,7 +5,7 @@
 #include "core/providers/cpu/math/gemm_base.h"
 #include "core/providers/cpu/math/gemm_helper.h"
 #include "core/providers/cpu/math/matmul_integer_base.h"
-#include "core/quantization/quant_util.h"
+#include "core/quantization/quantization.h"
 #include "core/util/math_cpuonly.h"
 
 namespace onnxruntime {
diff --git a/onnxruntime/core/providers/cpu/math/matmul_integer_base.h b/onnxruntime/core/providers/cpu/math/matmul_integer_base.h
index 8cb66b9361..8010eae3a8 100644
--- a/onnxruntime/core/providers/cpu/math/matmul_integer_base.h
+++ b/onnxruntime/core/providers/cpu/math/matmul_integer_base.h
@@ -4,7 +4,7 @@
 #include "core/framework/op_kernel.h"
 #include "core/mlas/inc/mlas.h"
 #include "core/providers/common.h"
-#include "core/quantization/quant_util.h"
+#include "core/quantization/quantization.h"
 
 namespace onnxruntime {
 
diff --git a/onnxruntime/core/quantization/quant_util.h b/onnxruntime/core/quantization/quant_util.h
deleted file mode 100644
index 7020fe2daa..0000000000
--- a/onnxruntime/core/quantization/quant_util.h
+++ /dev/null
@@ -1,22 +0,0 @@
-// Copyright (c) Microsoft Corporation. All rights reserved.
-// Licensed under the MIT License.
-
-#pragma once
-
-#include "core/common/common.h"
-#include "core/mlas/inc/mlas.h"
-#include "core/framework/allocator.h"
-#include "core/framework/buffer_deleter.h"
-
-namespace onnxruntime {
-namespace quantization {
-// Transpose the input and store it to a new allocated buffer
-inline uint8_t* TransPoseInputData(const uint8_t* input, BufferUniquePtr& buffer_holder, AllocatorPtr& allocator, size_t M, size_t N) {
-  uint8_t* output = static_cast<uint8_t*>(allocator->Alloc(M * N * sizeof(uint8_t)));
-  MlasTranspose(input, output, M, N);
-  buffer_holder.reset(output);
-  return output;
-}
-
-}  // namespace quantization
-}  // namespace onnxruntime
diff --git a/onnxruntime/core/quantization/quantization.h b/onnxruntime/core/quantization/quantization.h
index 834ac76fff..eb6d640866 100644
--- a/onnxruntime/core/quantization/quantization.h
+++ b/onnxruntime/core/quantization/quantization.h
@@ -186,5 +186,17 @@ void Dequantize(const std::vector<T>& values,
   Dequantize(values.data(), output.data(), params, values.size());
 }
 
+// Transpose the input and store it to a new allocated buffer.
+inline uint8_t* TransPoseInputData(const uint8_t* input,
+                                   BufferUniquePtr& buffer_holder,
+                                   AllocatorPtr& allocator,
+                                   size_t M,
+                                   size_t N) {
+  uint8_t* output = static_cast<uint8_t*>(allocator->Alloc(M * N * sizeof(uint8_t)));
+  MlasTranspose(input, output, M, N);
+  buffer_holder.reset(output);
+  return output;
+}
+
 }  // namespace quantization
 }  // namespace onnxruntime