diff --git a/onnxruntime/core/providers/cuda/cuda_execution_provider.cc b/onnxruntime/core/providers/cuda/cuda_execution_provider.cc
index 0ad7015519..19a18d0dc9 100644
--- a/onnxruntime/core/providers/cuda/cuda_execution_provider.cc
+++ b/onnxruntime/core/providers/cuda/cuda_execution_provider.cc
@@ -789,9 +789,9 @@ class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kO
 class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, int32_t, Resize);
 class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, uint8_t, Resize);
 class ONNX_OPERATOR_VERSIONED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 11, Clip);
-class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, float, Pad);
-class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, double, Pad);
-class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, MLFloat16, Pad);
+class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, float, Pad);
+class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, double, Pad);
+class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, MLFloat16, Pad);
 class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, bool, Equal);
 class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, int32_t, Equal);
 class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, int64_t, Equal);
@@ -1052,6 +1052,9 @@ class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain,
 class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 13, MLFloat16, LRN);
 class ONNX_OPERATOR_VERSIONED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 13, 13, Identity);
 class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 13, ScatterND);
+class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 13, float, Pad);
+class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 13, double, Pad);
+class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 13, MLFloat16, Pad);
 
 #if defined(CUDA_VERSION) && CUDA_VERSION >= 11000
 class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 13, 13, BFloat16, Add);
@@ -1605,9 +1608,9 @@ static Status RegisterCudaKernels(KernelRegistry& kernel_registry) {
     BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, int32_t, Resize)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, uint8_t, Resize)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 11, Clip)>,
-    BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, float, Pad)>,
-    BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, double, Pad)>,
-    BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, MLFloat16, Pad)>,
+    BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, float, Pad)>,
+    BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, double, Pad)>,
+    BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, MLFloat16, Pad)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, bool, Equal)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, int32_t, Equal)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 11, 12, int64_t, Equal)>,
@@ -1864,6 +1867,9 @@ static Status RegisterCudaKernels(KernelRegistry& kernel_registry) {
     BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 13, MLFloat16, LRN)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 13, 13, Identity)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 13, ScatterND)>,
+    BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 13, float, Pad)>,
+    BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 13, double, Pad)>,
+    BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 13, MLFloat16, Pad)>,
 #if defined(CUDA_VERSION) && CUDA_VERSION >= 11000
     BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 13, 13, BFloat16, Add)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 13, 13, BFloat16, Sub)>,
@@ -1925,7 +1931,7 @@ static Status RegisterCudaKernels(KernelRegistry& kernel_registry) {
     BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 14, float, BatchNormalization)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 14, double, BatchNormalization)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 14, MLFloat16, BatchNormalization)>,
-    #if defined(CUDA_VERSION) && CUDA_VERSION >= 11000
+#if defined(CUDA_VERSION) && CUDA_VERSION >= 11000
     BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 14, BFloat16, Add)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 14, BFloat16, Sub)>,
     BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kCudaExecutionProvider, kOnnxDomain, 14, BFloat16, Mul)>,
diff --git a/onnxruntime/core/providers/cuda/tensor/pad.cc b/onnxruntime/core/providers/cuda/tensor/pad.cc
index f76f209d21..26f5f975ce 100644
--- a/onnxruntime/core/providers/cuda/tensor/pad.cc
+++ b/onnxruntime/core/providers/cuda/tensor/pad.cc
@@ -18,10 +18,21 @@ namespace cuda {
       (*KernelDefBuilder::Create())                               \
           .TypeConstraint("T", DataTypeImpl::GetTensorType<T>()), \
       Pad<T>);                                                    \
+  ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_EX(                        \
+      Pad,                                                        \
+      kOnnxDomain,                                                \
+      11, 12,                                                     \
+      T,                                                          \
+      kCudaExecutionProvider,                                     \
+      (*KernelDefBuilder::Create())                               \
+          .InputMemoryType(OrtMemTypeCPUInput, 1)                 \
+          .InputMemoryType(OrtMemTypeCPUInput, 2)                 \
+          .TypeConstraint("T", DataTypeImpl::GetTensorType<T>()), \
+      Pad<T>);                                                    \
   ONNX_OPERATOR_TYPED_KERNEL_EX(                                  \
       Pad,                                                        \
       kOnnxDomain,                                                \
-      11,                                                         \
+      13,                                                         \
       T,                                                          \
       kCudaExecutionProvider,                                     \
       (*KernelDefBuilder::Create())                               \
diff --git a/onnxruntime/core/providers/rocm/rocm_execution_provider.cc b/onnxruntime/core/providers/rocm/rocm_execution_provider.cc
index 2805cb4d4e..ba74470fbe 100644
--- a/onnxruntime/core/providers/rocm/rocm_execution_provider.cc
+++ b/onnxruntime/core/providers/rocm/rocm_execution_provider.cc
@@ -767,9 +767,9 @@ class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain,
 class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, int32_t, Resize);
 class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, uint8_t, Resize);
 class ONNX_OPERATOR_VERSIONED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, 11, Clip);
-class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, float, Pad);
-class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, double, Pad);
-class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, MLFloat16, Pad);
+class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, 12, float, Pad);
+class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, 12, double, Pad);
+class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, 12, MLFloat16, Pad);
 class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, 12, bool, Equal);
 class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, 12, int32_t, Equal);
 class ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, 12, int64_t, Equal);
@@ -1017,6 +1017,9 @@ class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain,
 class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 13, MLFloat16, LRN);
 class ONNX_OPERATOR_VERSIONED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 13, 13, Identity);
 class ONNX_OPERATOR_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 13, ScatterND);
+class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 13, float, Pad);
+class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 13, double, Pad);
+class ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 13, MLFloat16, Pad);
 
 template <>
 KernelCreateInfo BuildKernelCreateInfo<void>() {
@@ -1496,9 +1499,9 @@ static Status RegisterRocmKernels(KernelRegistry& kernel_registry) {
       // BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, int32_t, Resize)>,
       // BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, uint8_t, Resize)>,
       BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, 11, Clip)>,
-      BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, float, Pad)>,
-      BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, double, Pad)>,
-      BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, MLFloat16, Pad)>,
+      BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, 12, float, Pad)>,
+      BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, 12, double, Pad)>,
+      BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, 12, MLFloat16, Pad)>,
       BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, 12, bool, Equal)>,
       BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, 12, int32_t, Equal)>,
       BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 11, 12, int64_t, Equal)>,
@@ -1742,6 +1745,9 @@ static Status RegisterRocmKernels(KernelRegistry& kernel_registry) {
       // BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 13, MLFloat16, LRN)>,
       BuildKernelCreateInfo<ONNX_OPERATOR_VERSIONED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 13, 13, Identity)>,
       BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 13, ScatterND)>,
+      BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 13, float, Pad)>,
+      BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 13, double, Pad)>,
+      BuildKernelCreateInfo<ONNX_OPERATOR_TYPED_KERNEL_CLASS_NAME(kRocmExecutionProvider, kOnnxDomain, 13, MLFloat16, Pad)>,
   };
 
   for (auto& function_table_entry : function_table) {