diff --git a/include/onnxruntime/core/framework/op_kernel.h b/include/onnxruntime/core/framework/op_kernel.h
index 00f3d5176e..4d615e87f8 100644
--- a/include/onnxruntime/core/framework/op_kernel.h
+++ b/include/onnxruntime/core/framework/op_kernel.h
@@ -16,7 +16,7 @@
 #include "core/common/status.h"
 #include "core/framework/execution_provider.h"
 #include "core/framework/kernel_def_builder.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/op_kernel_info.h"
 #include "core/framework/op_node_proto_helper.h"
 #include "core/framework/tensor.h"
diff --git a/include/onnxruntime/core/framework/op_kernel_info.h b/include/onnxruntime/core/framework/op_kernel_info.h
index 40b8c9a1fa..0259e7e68c 100644
--- a/include/onnxruntime/core/framework/op_kernel_info.h
+++ b/include/onnxruntime/core/framework/op_kernel_info.h
@@ -5,7 +5,7 @@
 
 #include "core/framework/execution_provider.h"
 #include "core/framework/kernel_def_builder.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/op_node_proto_helper.h"
 #include "core/graph/graph_viewer.h"
 #include "gsl/gsl"
diff --git a/include/onnxruntime/core/framework/ml_value.h b/include/onnxruntime/core/framework/ort_value.h
similarity index 100%
rename from include/onnxruntime/core/framework/ml_value.h
rename to include/onnxruntime/core/framework/ort_value.h
diff --git a/onnxruntime/core/dlpack/dlpack_converter.h b/onnxruntime/core/dlpack/dlpack_converter.h
index 4cd3885782..d8f794053d 100644
--- a/onnxruntime/core/dlpack/dlpack_converter.h
+++ b/onnxruntime/core/dlpack/dlpack_converter.h
@@ -5,7 +5,7 @@
 
 #pragma once
 
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include <dlpack/dlpack.h>
 
 namespace onnxruntime {
diff --git a/onnxruntime/core/framework/execution_frame.h b/onnxruntime/core/framework/execution_frame.h
index fbe8684f02..a94c2681f0 100644
--- a/onnxruntime/core/framework/execution_frame.h
+++ b/onnxruntime/core/framework/execution_frame.h
@@ -11,7 +11,7 @@
 #include "core/common/logging/logging.h"
 #include "core/common/status.h"
 #include "core/framework/iexecutor.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/node_index_info.h"
 #include "core/framework/sequential_execution_plan.h"
 #include "core/framework/tensor.h"
diff --git a/onnxruntime/core/framework/feeds_fetches_manager.h b/onnxruntime/core/framework/feeds_fetches_manager.h
index 889e3594c5..a15a08508f 100644
--- a/onnxruntime/core/framework/feeds_fetches_manager.h
+++ b/onnxruntime/core/framework/feeds_fetches_manager.h
@@ -7,7 +7,7 @@
 #include <vector>
 
 #ifndef SHARED_PROVIDER
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #endif
 
 namespace onnxruntime {
diff --git a/onnxruntime/core/framework/iexecutor.h b/onnxruntime/core/framework/iexecutor.h
index e6cd1589b7..f24094da3f 100644
--- a/onnxruntime/core/framework/iexecutor.h
+++ b/onnxruntime/core/framework/iexecutor.h
@@ -8,7 +8,7 @@
 
 #include "core/common/status.h"
 #include "core/framework/framework_common.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 
 struct OrtValue;
 namespace onnxruntime {
diff --git a/onnxruntime/core/framework/memory_info.cc b/onnxruntime/core/framework/memory_info.cc
index 3b72dbf929..2f09c90e50 100644
--- a/onnxruntime/core/framework/memory_info.cc
+++ b/onnxruntime/core/framework/memory_info.cc
@@ -1,7 +1,7 @@
 #if !defined(ORT_MINIMAL_BUILD) && defined(ORT_MEMORY_PROFILE)
 #include "core/framework/memory_info.h"
 #include "core/framework/mem_pattern.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 
 #include <fstream>
 #include <numeric>
diff --git a/onnxruntime/core/framework/node_index_info.h b/onnxruntime/core/framework/node_index_info.h
index b38a5fad7d..1f8cd4d46c 100644
--- a/onnxruntime/core/framework/node_index_info.h
+++ b/onnxruntime/core/framework/node_index_info.h
@@ -6,7 +6,7 @@
 #include <vector>
 
 #include "core/common/common.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/graph/basic_types.h"
 
 namespace onnxruntime {
diff --git a/onnxruntime/core/framework/ort_value_tensor_slicer.h b/onnxruntime/core/framework/ort_value_tensor_slicer.h
index 3069e79e9a..78b3d80eab 100644
--- a/onnxruntime/core/framework/ort_value_tensor_slicer.h
+++ b/onnxruntime/core/framework/ort_value_tensor_slicer.h
@@ -9,7 +9,7 @@
 
 #ifndef SHARED_PROVIDER
 #include "core/common/common.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/tensor.h"
 #endif
 
diff --git a/onnxruntime/core/framework/orttraining_partial_executor.h b/onnxruntime/core/framework/orttraining_partial_executor.h
index c3055c9327..d97396c972 100644
--- a/onnxruntime/core/framework/orttraining_partial_executor.h
+++ b/onnxruntime/core/framework/orttraining_partial_executor.h
@@ -10,7 +10,7 @@
 #include "core/common/logging/logging.h"
 #include "core/framework/iexecutor.h"
 #include "core/framework/framework_common.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/session_state.h"
 #include "core/graph/graph_viewer.h"
 #include "core/framework/op_kernel_context_internal.h"
diff --git a/onnxruntime/core/framework/parallel_executor.h b/onnxruntime/core/framework/parallel_executor.h
index 799469f353..ef2eebbf51 100644
--- a/onnxruntime/core/framework/parallel_executor.h
+++ b/onnxruntime/core/framework/parallel_executor.h
@@ -9,7 +9,7 @@
 #include "core/common/logging/logging.h"
 #include "core/framework/iexecutor.h"
 #include "core/framework/framework_common.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/session_state.h"
 #include "core/graph/graph_viewer.h"
 #include "core/platform/ort_mutex.h"
diff --git a/onnxruntime/core/framework/sequential_executor.h b/onnxruntime/core/framework/sequential_executor.h
index b7c05b1e8b..463749d747 100644
--- a/onnxruntime/core/framework/sequential_executor.h
+++ b/onnxruntime/core/framework/sequential_executor.h
@@ -10,7 +10,7 @@
 #include "core/common/logging/logging.h"
 #include "core/framework/iexecutor.h"
 #include "core/framework/framework_common.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/session_state.h"
 #include "core/graph/graph_viewer.h"
 #include "core/framework/op_kernel_context_internal.h"
diff --git a/onnxruntime/core/framework/session_options.cc b/onnxruntime/core/framework/session_options.cc
index 517930791f..2e41b05440 100644
--- a/onnxruntime/core/framework/session_options.cc
+++ b/onnxruntime/core/framework/session_options.cc
@@ -3,7 +3,7 @@
 
 #include "core/framework/session_options.h"
 #include "core/common/logging/logging.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 
 namespace onnxruntime {
 
diff --git a/onnxruntime/core/framework/session_state.h b/onnxruntime/core/framework/session_state.h
index aa21e6b82f..90b6f7e70c 100644
--- a/onnxruntime/core/framework/session_state.h
+++ b/onnxruntime/core/framework/session_state.h
@@ -23,7 +23,7 @@
 #include "core/framework/fuse_nodes_funcs.h"
 #include "core/framework/kernel_registry_manager.h"
 #include "core/framework/mem_pattern.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/node_index_info.h"
 #include "core/framework/op_kernel.h"
 #include "core/framework/ort_value_name_idx_map.h"
diff --git a/onnxruntime/core/framework/session_state_utils.cc b/onnxruntime/core/framework/session_state_utils.cc
index c64cd30b65..ae22c4a3c2 100644
--- a/onnxruntime/core/framework/session_state_utils.cc
+++ b/onnxruntime/core/framework/session_state_utils.cc
@@ -14,7 +14,7 @@
 #include "core/graph/graph_viewer.h"
 #include "core/framework/data_transfer_manager.h"
 #include "core/framework/graph_partitioner.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/ort_value_pattern_planner.h"
 #include "core/framework/ort_value_name_idx_map.h"
 #include "core/framework/sequential_execution_plan.h"
diff --git a/onnxruntime/core/framework/tensor.cc b/onnxruntime/core/framework/tensor.cc
index a3796a04c4..01ca218ba8 100644
--- a/onnxruntime/core/framework/tensor.cc
+++ b/onnxruntime/core/framework/tensor.cc
@@ -7,7 +7,7 @@
 #include "core/common/safeint.h"
 #include "core/framework/allocatormgr.h"
 #include "core/framework/data_types.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/utils.h"
 
 namespace onnxruntime {
diff --git a/onnxruntime/core/framework/tensor_type_and_shape.cc b/onnxruntime/core/framework/tensor_type_and_shape.cc
index 712150e0c4..fa512f629b 100644
--- a/onnxruntime/core/framework/tensor_type_and_shape.cc
+++ b/onnxruntime/core/framework/tensor_type_and_shape.cc
@@ -9,7 +9,7 @@
 
 #include "core/common/safeint.h"
 #include "core/framework/error_code_helper.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/onnxruntime_typeinfo.h"
 #include "core/framework/sparse_tensor.h"
 #include "core/framework/tensor_shape.h"
diff --git a/onnxruntime/core/framework/tensorprotoutils.h b/onnxruntime/core/framework/tensorprotoutils.h
index df616ff282..14ce999008 100644
--- a/onnxruntime/core/framework/tensorprotoutils.h
+++ b/onnxruntime/core/framework/tensorprotoutils.h
@@ -12,7 +12,7 @@
 #include "core/common/status.h"
 #include "core/framework/endian_utils.h"
 #include "core/framework/allocator.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/mem_buffer.h"
 #include "core/framework/tensor_external_data_info.h"
 #include "core/graph/onnx_protobuf.h"
diff --git a/onnxruntime/core/language_interop_ops/pyop/pyop.h b/onnxruntime/core/language_interop_ops/pyop/pyop.h
index ffec205815..14c32238f9 100644
--- a/onnxruntime/core/language_interop_ops/pyop/pyop.h
+++ b/onnxruntime/core/language_interop_ops/pyop/pyop.h
@@ -1,7 +1,7 @@
 #pragma once
 #include "core/platform/env.h"
 #define LOAD_PYOP_SYM(n,v,m) ORT_ENFORCE(Env::Default().GetSymbolFromLibrary(handle_,n,reinterpret_cast<void**>(&v))==Status::OK(),m)
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/session/onnxruntime_cxx_api.h"
 #include "core/framework/op_kernel_context_internal.h"
 #include <iostream>
diff --git a/onnxruntime/core/optimizer/constant_folding.h b/onnxruntime/core/optimizer/constant_folding.h
index 30bc4b2c7c..ef18b65c09 100644
--- a/onnxruntime/core/optimizer/constant_folding.h
+++ b/onnxruntime/core/optimizer/constant_folding.h
@@ -4,7 +4,7 @@
 #pragma once
 
 #include "core/optimizer/graph_transformer.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include <memory>
 #include "core/framework/execution_provider.h"
 
diff --git a/onnxruntime/core/optimizer/optimizer_execution_frame.h b/onnxruntime/core/optimizer/optimizer_execution_frame.h
index 99135bcd89..385640beee 100644
--- a/onnxruntime/core/optimizer/optimizer_execution_frame.h
+++ b/onnxruntime/core/optimizer/optimizer_execution_frame.h
@@ -10,7 +10,7 @@
 #include "core/framework/data_transfer_manager.h"
 #include "core/framework/execution_frame.h"
 #include "core/framework/ort_value_name_idx_map.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/callback.h"
 
 namespace onnxruntime {
diff --git a/onnxruntime/core/providers/cpu/controlflow/scan_utils.h b/onnxruntime/core/providers/cpu/controlflow/scan_utils.h
index 0d17ede9d0..6e36fe2f28 100644
--- a/onnxruntime/core/providers/cpu/controlflow/scan_utils.h
+++ b/onnxruntime/core/providers/cpu/controlflow/scan_utils.h
@@ -9,7 +9,7 @@
 #include "core/common/common.h"
 #include "core/framework/allocator.h"
 #include "core/framework/feeds_fetches_manager.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/ort_value_tensor_slicer.h"
 #include "core/graph/onnx_protobuf.h"
 #include "core/providers/cpu/controlflow/scan.h"
diff --git a/onnxruntime/core/providers/cpu/controlflow/utils.h b/onnxruntime/core/providers/cpu/controlflow/utils.h
index 5aa749fde1..108d37c004 100644
--- a/onnxruntime/core/providers/cpu/controlflow/utils.h
+++ b/onnxruntime/core/providers/cpu/controlflow/utils.h
@@ -9,7 +9,7 @@
 
 #include "core/framework/feeds_fetches_manager.h"
 #ifdef SHARED_PROVIDER
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #else
 #include "core/framework/op_kernel.h"
 #endif
diff --git a/onnxruntime/core/providers/cuda/controlflow/loop.cc b/onnxruntime/core/providers/cuda/controlflow/loop.cc
index cb5a38bb6c..73d82d666f 100644
--- a/onnxruntime/core/providers/cuda/controlflow/loop.cc
+++ b/onnxruntime/core/providers/cuda/controlflow/loop.cc
@@ -5,7 +5,7 @@
 #include "core/providers/cuda/controlflow/loop.h"
 #include "core/providers/cuda/cuda_common.h"
 #include "core/providers/cuda/cuda_fwd.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 
 using namespace ONNX_NAMESPACE;
 using namespace onnxruntime::common;
diff --git a/onnxruntime/core/providers/cuda/controlflow/scan.cc b/onnxruntime/core/providers/cuda/controlflow/scan.cc
index 71caf71611..abd9375b9a 100644
--- a/onnxruntime/core/providers/cuda/controlflow/scan.cc
+++ b/onnxruntime/core/providers/cuda/controlflow/scan.cc
@@ -6,7 +6,7 @@
 
 #include "core/providers/cuda/cuda_common.h"
 #include "core/providers/cuda/tensor/transpose.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 
 // TODO: It's ugly to include a .cc file but this .cc file defines the implementation of some templates which we need.
 #include "core/framework/ort_value_tensor_slicer.cc"
diff --git a/onnxruntime/core/session/IOBinding.h b/onnxruntime/core/session/IOBinding.h
index 4989308f74..2b97dbeb22 100644
--- a/onnxruntime/core/session/IOBinding.h
+++ b/onnxruntime/core/session/IOBinding.h
@@ -9,7 +9,7 @@
 #include "core/framework/execution_provider.h"
 #include "core/common/status.h"
 #include "core/graph/basic_types.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/session/inference_session.h"
 #include "core/common/logging/logging.h"
 
diff --git a/onnxruntime/core/session/onnxruntime_c_api.cc b/onnxruntime/core/session/onnxruntime_c_api.cc
index 6cad6ad527..6a027e403f 100644
--- a/onnxruntime/core/session/onnxruntime_c_api.cc
+++ b/onnxruntime/core/session/onnxruntime_c_api.cc
@@ -23,7 +23,7 @@
 #include "core/graph/graph.h"
 #include "core/framework/allocator.h"
 #include "core/framework/tensor.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/providers/get_execution_providers.h"
 #include "core/session/environment.h"
 #include "core/framework/callback.h"
diff --git a/onnxruntime/python/onnxruntime_pybind_iobinding.cc b/onnxruntime/python/onnxruntime_pybind_iobinding.cc
index 9573e54f30..852dd2a136 100644
--- a/onnxruntime/python/onnxruntime_pybind_iobinding.cc
+++ b/onnxruntime/python/onnxruntime_pybind_iobinding.cc
@@ -10,7 +10,7 @@
 #define PY_ARRAY_UNIQUE_SYMBOL onnxruntime_python_ARRAY_API
 #include <numpy/arrayobject.h>
 
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/tensor.h"
 #include "core/framework/tensorprotoutils.h"
 #include "core/framework/TensorSeq.h"
diff --git a/onnxruntime/python/onnxruntime_pybind_mlvalue.h b/onnxruntime/python/onnxruntime_pybind_mlvalue.h
index 79406a7322..f5631a3c92 100644
--- a/onnxruntime/python/onnxruntime_pybind_mlvalue.h
+++ b/onnxruntime/python/onnxruntime_pybind_mlvalue.h
@@ -14,7 +14,7 @@
 #include "core/common/logging/sinks/cerr_sink.h"
 #include "core/framework/allocatormgr.h"
 #include "core/session/environment.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/session/inference_session.h"
 
 namespace onnxruntime {
diff --git a/onnxruntime/python/onnxruntime_pybind_ortvalue.cc b/onnxruntime/python/onnxruntime_pybind_ortvalue.cc
index a154170b32..ade210bc33 100644
--- a/onnxruntime/python/onnxruntime_pybind_ortvalue.cc
+++ b/onnxruntime/python/onnxruntime_pybind_ortvalue.cc
@@ -10,7 +10,7 @@
 #define PY_ARRAY_UNIQUE_SYMBOL onnxruntime_python_ARRAY_API
 #include <numpy/arrayobject.h>
 
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/tensor.h"
 #include "core/framework/sparse_tensor.h"
 #include "core/framework/TensorSeq.h"
diff --git a/onnxruntime/test/framework/test_utils.h b/onnxruntime/test/framework/test_utils.h
index e99bc4b825..9d5633ea34 100644
--- a/onnxruntime/test/framework/test_utils.h
+++ b/onnxruntime/test/framework/test_utils.h
@@ -8,7 +8,7 @@
 #include "core/framework/allocatormgr.h"
 #include "core/framework/execution_provider.h"
 #include "core/providers/cpu/cpu_execution_provider.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 
 #include "gsl/gsl"
 
diff --git a/onnxruntime/test/optimizer/graph_transform_test.cc b/onnxruntime/test/optimizer/graph_transform_test.cc
index 4b4fb9ba5e..d981343f65 100644
--- a/onnxruntime/test/optimizer/graph_transform_test.cc
+++ b/onnxruntime/test/optimizer/graph_transform_test.cc
@@ -10,7 +10,7 @@
 
 #include "asserts.h"
 #include "core/framework/data_types.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/graph/graph_utils.h"
 #include "core/graph/graph_viewer.h"
 #include "core/graph/model.h"
diff --git a/onnxruntime/test/optimizer/optimizer_test.cc b/onnxruntime/test/optimizer/optimizer_test.cc
index c5947c380b..b3b4f4c2b5 100644
--- a/onnxruntime/test/optimizer/optimizer_test.cc
+++ b/onnxruntime/test/optimizer/optimizer_test.cc
@@ -8,7 +8,7 @@
 #include "core/optimizer/graph_transformer.h"
 #include "core/optimizer/graph_transformer_mgr.h"
 #include "core/framework/data_types.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/op_kernel.h"
 #include "core/util/math.h"
 #include "core/platform/env.h"
diff --git a/onnxruntime/test/util/include/test/compare_ortvalue.h b/onnxruntime/test/util/include/test/compare_ortvalue.h
index ac1ef18857..da70f87ecd 100644
--- a/onnxruntime/test/util/include/test/compare_ortvalue.h
+++ b/onnxruntime/test/util/include/test/compare_ortvalue.h
@@ -4,7 +4,7 @@
 #pragma once
 // TODO(): move compare_mlvalue.{h,cc} to test dir
 
-#include <core/framework/ml_value.h>
+#include <core/framework/ort_value.h>
 #include <string>
 
 namespace ONNX_NAMESPACE {
diff --git a/onnxruntime/test/util/test_utils.cc b/onnxruntime/test/util/test_utils.cc
index 025a339da8..152e44bec3 100644
--- a/onnxruntime/test/util/test_utils.cc
+++ b/onnxruntime/test/util/test_utils.cc
@@ -3,7 +3,7 @@
 
 #include "test/util/include/test_utils.h"
 
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/session/inference_session.h"
 
 #include "test/util/include/asserts.h"
diff --git a/orttraining/orttraining/core/framework/checkpointing.cc b/orttraining/orttraining/core/framework/checkpointing.cc
index 7ef4e95fe8..e87a7e6566 100644
--- a/orttraining/orttraining/core/framework/checkpointing.cc
+++ b/orttraining/orttraining/core/framework/checkpointing.cc
@@ -13,7 +13,7 @@
 #include "core/common/path.h"
 #include "core/framework/data_transfer_utils.h"
 #include "core/framework/endian_utils.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/tensor_external_data_info.h"
 #include "core/framework/tensorprotoutils.h"
 #include "core/platform/env.h"
diff --git a/orttraining/orttraining/core/framework/pipeline.h b/orttraining/orttraining/core/framework/pipeline.h
index 93e95590d9..b5a58857cd 100644
--- a/orttraining/orttraining/core/framework/pipeline.h
+++ b/orttraining/orttraining/core/framework/pipeline.h
@@ -14,7 +14,7 @@
 
 #include "gsl/gsl"
 #include "orttraining/core/framework/distributed_run_context.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 
 namespace onnxruntime {
 namespace training {
diff --git a/orttraining/orttraining/core/framework/torch/torch_proxy.h b/orttraining/orttraining/core/framework/torch/torch_proxy.h
index 29ef4ce9fc..b83a3c553a 100644
--- a/orttraining/orttraining/core/framework/torch/torch_proxy.h
+++ b/orttraining/orttraining/core/framework/torch/torch_proxy.h
@@ -6,7 +6,7 @@
 #include "orttraining/core/framework/torch/python_common.h"
 
 #ifndef SHARED_PROVIDER
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/op_kernel_context_internal.h"
 #include "core/platform/env.h"
 #endif
diff --git a/orttraining/orttraining/core/graph/optimizer/adam_optimizer_builder.cc b/orttraining/orttraining/core/graph/optimizer/adam_optimizer_builder.cc
index 90dc30f2c1..357c98c4af 100644
--- a/orttraining/orttraining/core/graph/optimizer/adam_optimizer_builder.cc
+++ b/orttraining/orttraining/core/graph/optimizer/adam_optimizer_builder.cc
@@ -4,7 +4,7 @@
 #include "orttraining/core/graph/optimizer/adam_optimizer_builder.h"
 #include "orttraining/core/graph/graph_augmenter.h"
 #include "core/util/math.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/tensorprotoutils.h"
 
 namespace onnxruntime {
diff --git a/orttraining/orttraining/core/graph/optimizer/lamb_optimizer_builder.cc b/orttraining/orttraining/core/graph/optimizer/lamb_optimizer_builder.cc
index 609bdc0930..1a3ed2ea7a 100644
--- a/orttraining/orttraining/core/graph/optimizer/lamb_optimizer_builder.cc
+++ b/orttraining/orttraining/core/graph/optimizer/lamb_optimizer_builder.cc
@@ -5,7 +5,7 @@
 #include "orttraining/core/graph/optimizer/lamb_optimizer_builder.h"
 #include "orttraining/core/graph/optimizer_builder.h"
 #include "orttraining/core/graph/graph_augmenter.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/tensorprotoutils.h"
 #include "core/util/math.h"
 #include "onnx/defs/attr_proto_util.h"
diff --git a/orttraining/orttraining/core/graph/optimizer_config.h b/orttraining/orttraining/core/graph/optimizer_config.h
index 934c431e13..4dca9c2ce5 100644
--- a/orttraining/orttraining/core/graph/optimizer_config.h
+++ b/orttraining/orttraining/core/graph/optimizer_config.h
@@ -10,7 +10,7 @@
 #include "core/framework/framework_common.h"
 #include "core/graph/node_arg.h"
 #endif
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 
 namespace onnxruntime {
 namespace training {
diff --git a/orttraining/orttraining/core/session/tensor_helper.h b/orttraining/orttraining/core/session/tensor_helper.h
index b09b9a9fe2..6a0647d104 100644
--- a/orttraining/orttraining/core/session/tensor_helper.h
+++ b/orttraining/orttraining/core/session/tensor_helper.h
@@ -1,7 +1,7 @@
 // Copyright (c) Microsoft Corporation. All rights reserved.
 // Licensed under the MIT License.
 
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/session/inference_session.h"
 
 namespace onnxruntime {
diff --git a/orttraining/orttraining/eager/ort_aten.h b/orttraining/orttraining/eager/ort_aten.h
index 1cee2a2443..977660fde2 100644
--- a/orttraining/orttraining/eager/ort_aten.h
+++ b/orttraining/orttraining/eager/ort_aten.h
@@ -4,7 +4,7 @@
 #pragma once
 
 #include <torch/extension.h>
-#include <core/framework/ml_value.h>
+#include <core/framework/ort_value.h>
 
 #include "ort_util.h"
 #include "ort_ops.h"
diff --git a/orttraining/orttraining/eager/ort_backends.h b/orttraining/orttraining/eager/ort_backends.h
index 1a11458acb..5cd77f272d 100644
--- a/orttraining/orttraining/eager/ort_backends.h
+++ b/orttraining/orttraining/eager/ort_backends.h
@@ -4,7 +4,7 @@
 #pragma once
 
 #include <torch/extension.h>
-#include <core/framework/ml_value.h>
+#include <core/framework/ort_value.h>
 #include "core/common/status.h"
 #include <core/framework/provider_options.h>
 #include <core/eager/ort_kernel_invoker.h>
diff --git a/orttraining/orttraining/eager/ort_ops.h b/orttraining/orttraining/eager/ort_ops.h
index c9e005cc33..cb78d011b0 100644
--- a/orttraining/orttraining/eager/ort_ops.h
+++ b/orttraining/orttraining/eager/ort_ops.h
@@ -3,7 +3,7 @@
 
 #pragma once
 
-#include <core/framework/ml_value.h>
+#include <core/framework/ort_value.h>
 #include <core/eager/ort_kernel_invoker.h>
 
 namespace torch_ort {
diff --git a/orttraining/orttraining/eager/ort_tensor.h b/orttraining/orttraining/eager/ort_tensor.h
index 86d6caab5d..2777d30f48 100644
--- a/orttraining/orttraining/eager/ort_tensor.h
+++ b/orttraining/orttraining/eager/ort_tensor.h
@@ -4,7 +4,7 @@
 #pragma once
 
 #include <c10/core/TensorImpl.h>
-#include <core/framework/ml_value.h>
+#include <core/framework/ort_value.h>
 
 namespace torch_ort {
 namespace eager {
diff --git a/orttraining/orttraining/models/runner/data_loader.h b/orttraining/orttraining/models/runner/data_loader.h
index 5fd53d346b..cc6f8470a6 100644
--- a/orttraining/orttraining/models/runner/data_loader.h
+++ b/orttraining/orttraining/models/runner/data_loader.h
@@ -10,7 +10,7 @@
 #include "core/common/common.h"
 #include "core/common/path_string.h"
 #include "core/framework/framework_common.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/platform/path_lib.h"
 #include "core/platform/threadpool.h"
 #include "orttraining/models/runner/training_util.h"
diff --git a/orttraining/orttraining/models/runner/training_runner.h b/orttraining/orttraining/models/runner/training_runner.h
index 5a4fb1f5ee..50623c8e88 100644
--- a/orttraining/orttraining/models/runner/training_runner.h
+++ b/orttraining/orttraining/models/runner/training_runner.h
@@ -7,7 +7,7 @@
 #include <vector>
 
 #include "core/common/path_string.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/providers/providers.h"
 #include "orttraining/core/framework/checkpoint_registry.h"
 #include "orttraining/core/framework/communication/mpi/mpi_context.h"
diff --git a/orttraining/orttraining/models/runner/training_util.h b/orttraining/orttraining/models/runner/training_util.h
index af4e6f266c..76013b578e 100644
--- a/orttraining/orttraining/models/runner/training_util.h
+++ b/orttraining/orttraining/models/runner/training_util.h
@@ -6,7 +6,7 @@
 #include <math.h>
 #include "constant.h"
 #include "core/framework/callback.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/framework_common.h"
 #include "core/providers/cpu/cpu_execution_provider.h"
 
diff --git a/orttraining/orttraining/test/framework/checkpointing_test.cc b/orttraining/orttraining/test/framework/checkpointing_test.cc
index 9e1981aece..05b13a8ffa 100644
--- a/orttraining/orttraining/test/framework/checkpointing_test.cc
+++ b/orttraining/orttraining/test/framework/checkpointing_test.cc
@@ -10,7 +10,7 @@
 
 #include "core/common/common.h"
 #include "core/framework/data_transfer.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "core/framework/tensor.h"
 #include "core/framework/tensorprotoutils.h"
 #include "core/platform/path_lib.h"
diff --git a/orttraining/orttraining/training_ops/cuda/loss/softmax_cross_entropy_loss_impl.cc b/orttraining/orttraining/training_ops/cuda/loss/softmax_cross_entropy_loss_impl.cc
index c60e1999a2..bccfebbca5 100644
--- a/orttraining/orttraining/training_ops/cuda/loss/softmax_cross_entropy_loss_impl.cc
+++ b/orttraining/orttraining/training_ops/cuda/loss/softmax_cross_entropy_loss_impl.cc
@@ -4,7 +4,7 @@
 #include "core/providers/cuda/math/softmax.h"
 #include "core/providers/cuda/reduction/reduction_functions.h"
 #include "core/providers/cuda/tensor/transpose.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 #include "orttraining/training_ops/cpu/loss/softmax_cross_entropy_loss.h"
 #include "orttraining/training_ops/cuda/loss/softmax_cross_entropy_loss_impl.h"
 
diff --git a/orttraining/orttraining/training_ops/cuda/torch/torch_custom_function_kernel.cc b/orttraining/orttraining/training_ops/cuda/torch/torch_custom_function_kernel.cc
index 79b71c9acc..eb376760ef 100644
--- a/orttraining/orttraining/training_ops/cuda/torch/torch_custom_function_kernel.cc
+++ b/orttraining/orttraining/training_ops/cuda/torch/torch_custom_function_kernel.cc
@@ -6,7 +6,7 @@
 #include "core/providers/shared_library/provider_api.h"
 #include "orttraining/core/framework/torch/refcount_tracker.h"
 #include "orttraining/training_ops/cuda/torch/torch_custom_function_kernel.h"
-#include "core/framework/ml_value.h"
+#include "core/framework/ort_value.h"
 
 using namespace onnxruntime::language_interop_ops::torch;
 
diff --git a/winml/test/model/compare_feature_value.cpp b/winml/test/model/compare_feature_value.cpp
index a7eaa351f4..a87a4b5546 100644
--- a/winml/test/model/compare_feature_value.cpp
+++ b/winml/test/model/compare_feature_value.cpp
@@ -1,7 +1,7 @@
 #include "testPch.h"
 #include "compare_feature_value.h"
 #include "StringHelpers.h"
-#include <core/framework/ml_value.h>
+#include <core/framework/ort_value.h>
 #include "ort_value_helper.h"
 
 using namespace winrt::Windows::Foundation::Collections;