onnxruntime-directml 1.21.1__cp313-cp313-win_amd64.whl → 1.22.0__cp313-cp313-win_amd64.whl

onnxruntime/ThirdPartyNotices.txt

@@ -6080,3 +6080,77 @@ https://dawn.googlesource.com/dawn
    CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
    OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
    OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+_____
+
+KleidiAI
+
+https://gitlab.arm.com/kleidi/kleidiai
+
+Apache License
+Version 2.0, January 2004
+http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+"License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document.
+
+"Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License.
+
+"Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity.
+
+"You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License.
+
+"Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files.
+
+"Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.
+
+"Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below).
+
+"Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof.
+
+"Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."
+
+"Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions:
+
+     (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and
+
+     (b) You must cause any modified files to carry prominent notices stating that You changed the files; and
+
+     (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and
+
+     (d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License.
+
+     You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS
+
+Copyright 2024-2025 Arm Limited and/or its affiliates <open-source-office@arm.com>
+
+Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

onnxruntime/__init__.py

@@ -8,7 +8,7 @@ For more information on ONNX Runtime, please see `aka.ms/onnxruntime <https://ak
 or the `Github project <https://github.com/microsoft/onnxruntime/>`_.
 """
 
-__version__ = "1.21.1"
+__version__ = "1.22.0"
 __author__ = "Microsoft"
 
 # we need to do device version validation (for example to check Cuda version for an onnxruntime-training package).

onnxruntime/capi/build_and_package_info.py

@@ -1,2 +1,2 @@
 package_name = 'onnxruntime-directml'
-__version__ = '1.21.1'
+__version__ = '1.22.0'

onnxruntime/capi/onnxruntime_inference_collection.py

@@ -15,6 +15,9 @@ from typing import Any
 from onnxruntime.capi import _pybind_state as C
 
 if typing.TYPE_CHECKING:
+    import numpy as np
+    import numpy.typing as npt
+
     import onnxruntime
 
 
@@ -59,22 +62,22 @@ class AdapterFormat:
         """
         self._adapter.export_adapter(file_path)
 
-    def get_format_version(self):
+    def get_format_version(self) -> int:
         return self._adapter.format_version
 
-    def set_adapter_version(self, adapter_version: int):
+    def set_adapter_version(self, adapter_version: int) -> None:
         self._adapter.adapter_version = adapter_version
 
-    def get_adapter_version(self):
+    def get_adapter_version(self) -> int:
         return self._adapter.adapter_version
 
-    def set_model_version(self, model_version: int):
+    def set_model_version(self, model_version: int) -> None:
         self._adapter.model_version = model_version
 
-    def get_model_version(self):
+    def get_model_version(self) -> int:
         return self._adapter.model_version
 
-    def set_parameters(self, params: dict[str, OrtValue]):
+    def set_parameters(self, params: dict[str, OrtValue]) -> None:
         self._adapter.parameters = {k: v._ortvalue for k, v in params.items()}
 
     def get_parameters(self) -> dict[str, OrtValue]:
@@ -174,27 +177,27 @@ class Session:
         self._sess = None
         self._enable_fallback = True
 
-    def get_session_options(self):
+    def get_session_options(self) -> onnxruntime.SessionOptions:
         "Return the session options. See :class:`onnxruntime.SessionOptions`."
         return self._sess_options
 
-    def get_inputs(self):
+    def get_inputs(self) -> Sequence[onnxruntime.NodeArg]:
         "Return the inputs metadata as a list of :class:`onnxruntime.NodeArg`."
         return self._inputs_meta
 
-    def get_outputs(self):
+    def get_outputs(self) -> Sequence[onnxruntime.NodeArg]:
         "Return the outputs metadata as a list of :class:`onnxruntime.NodeArg`."
         return self._outputs_meta
 
-    def get_overridable_initializers(self):
+    def get_overridable_initializers(self) -> Sequence[onnxruntime.NodeArg]:
         "Return the inputs (including initializers) metadata as a list of :class:`onnxruntime.NodeArg`."
         return self._overridable_initializers
 
-    def get_modelmeta(self):
+    def get_modelmeta(self) -> onnxruntime.ModelMetadata:
         "Return the metadata. See :class:`onnxruntime.ModelMetadata`."
         return self._model_meta
 
-    def get_providers(self):
+    def get_providers(self) -> Sequence[str]:
         "Return list of registered execution providers."
         return self._providers
 
@@ -202,7 +205,7 @@ class Session:
         "Return registered execution providers' configurations."
         return self._provider_options
 
-    def set_providers(self, providers=None, provider_options=None):
+    def set_providers(self, providers=None, provider_options=None) -> None:
         """
         Register the input list of execution providers. The underlying session is re-created.
 
@@ -224,13 +227,13 @@ class Session:
         # recreate the underlying C.InferenceSession
         self._reset_session(providers, provider_options)
 
-    def disable_fallback(self):
+    def disable_fallback(self) -> None:
         """
         Disable session.run() fallback mechanism.
         """
         self._enable_fallback = False
 
-    def enable_fallback(self):
+    def enable_fallback(self) -> None:
         """
         Enable session.Run() fallback mechanism. If session.Run() fails due to an internal Execution Provider failure,
         reset the Execution Providers enabled for this session.
@@ -249,7 +252,7 @@ class Session:
                 f"Required inputs ({missing_input_names}) are missing from input feed ({feed_input_names})."
             )
 
-    def run(self, output_names, input_feed, run_options=None):
+    def run(self, output_names, input_feed, run_options=None) -> Sequence[np.ndarray | SparseTensor | list | dict]:
         """
         Compute the predictions.
 
@@ -308,7 +311,7 @@ class Session:
             output_names = [output.name for output in self._outputs_meta]
         return self._sess.run_async(output_names, input_feed, callback, user_data, run_options)
 
-    def run_with_ort_values(self, output_names, input_dict_ort_values, run_options=None):
+    def run_with_ort_values(self, output_names, input_dict_ort_values, run_options=None) -> Sequence[OrtValue]:
         """
         Compute the predictions.
 
@@ -367,7 +370,7 @@ class Session:
         """
         return self._sess.get_profiling_start_time_ns
 
-    def io_binding(self):
+    def io_binding(self) -> IOBinding:
         "Return an onnxruntime.IOBinding object`."
         return IOBinding(self)
 
@@ -504,6 +507,23 @@ class InferenceSession(Session):
                 self._fallback_providers = ["CUDAExecutionProvider", "CPUExecutionProvider"]
             else:
                 self._fallback_providers = ["CPUExecutionProvider"]
+        if "NvTensorRTRTXExecutionProvider" in available_providers:
+            if (
+                providers
+                and any(
+                    provider == "CUDAExecutionProvider"
+                    or (isinstance(provider, tuple) and provider[0] == "CUDAExecutionProvider")
+                    for provider in providers
+                )
+                and any(
+                    provider == "NvTensorRTRTXExecutionProvider"
+                    or (isinstance(provider, tuple) and provider[0] == "NvExecutionProvider")
+                    for provider in providers
+                )
+            ):
+                self._fallback_providers = ["CUDAExecutionProvider", "CPUExecutionProvider"]
+            else:
+                self._fallback_providers = ["CPUExecutionProvider"]
         # MIGraphX can fall back to ROCM if it's explicitly assigned. All others fall back to CPU.
         elif "MIGraphXExecutionProvider" in available_providers:
             if providers and any(
@@ -550,7 +570,7 @@ class InferenceSession(Session):
         self._provider_options = self._sess.get_provider_options()
         self._profiling_start_time_ns = self._sess.get_profiling_start_time_ns
 
-    def _reset_session(self, providers, provider_options):
+    def _reset_session(self, providers, provider_options) -> None:
         "release underlying session object."
         # meta data references session internal structures
         # so they must be set to None to decrement _sess reference count.
@@ -579,6 +599,15 @@ class InferenceSession(Session):
             ):
                 C.register_tensorrt_plugins_as_custom_ops(session_options, providers[i][1])
 
+            if providers[i] in available_providers and providers[i] == "NvTensorRTRTXExecutionProvider":
+                C.register_nv_tensorrt_rtx_plugins_as_custom_ops(session_options, provider_options[i])
+            elif (
+                isinstance(providers[i], tuple)
+                and providers[i][0] in available_providers
+                and providers[i][0] == "NvTensorrtRTXExecutionProvider"
+            ):
+                C.register_nv_tensorrt_rtx_plugins_as_custom_ops(session_options, providers[i][1])
+
 
 class IOBinding:
     """
@@ -721,7 +750,7 @@ class OrtValue:
     This class provides APIs to construct and deal with OrtValues.
     """
 
-    def __init__(self, ortvalue, numpy_obj=None):
+    def __init__(self, ortvalue: C.OrtValue, numpy_obj: np.ndarray | None = None):
         if isinstance(ortvalue, C.OrtValue):
             self._ortvalue = ortvalue
             # Hold a ref count to the numpy object if the OrtValue is backed directly
@@ -733,11 +762,11 @@ class OrtValue:
                 "`Provided ortvalue` needs to be of type `onnxruntime.capi.onnxruntime_pybind11_state.OrtValue`"
             )
 
-    def _get_c_value(self):
+    def _get_c_value(self) -> C.OrtValue:
         return self._ortvalue
 
-    @staticmethod
-    def ortvalue_from_numpy(numpy_obj, device_type="cpu", device_id=0):
+    @classmethod
+    def ortvalue_from_numpy(cls, numpy_obj: np.ndarray, /, device_type="cpu", device_id=0) -> OrtValue:
         """
         Factory method to construct an OrtValue (which holds a Tensor) from a given Numpy object
         A copy of the data in the Numpy object is held by the OrtValue only if the device is NOT cpu
@@ -749,7 +778,7 @@ class OrtValue:
         # Hold a reference to the numpy object (if device_type is 'cpu') as the OrtValue
         # is backed directly by the data buffer of the numpy object and so the numpy object
         # must be around until this OrtValue instance is around
-        return OrtValue(
+        return cls(
             C.OrtValue.ortvalue_from_numpy(
                 numpy_obj,
                 C.OrtDevice(
@@ -761,8 +790,8 @@ class OrtValue:
             numpy_obj if device_type.lower() == "cpu" else None,
         )
 
-    @staticmethod
-    def ortvalue_from_numpy_with_onnx_type(data, onnx_element_type: int):
+    @classmethod
+    def ortvalue_from_numpy_with_onnx_type(cls, data: np.ndarray, /, onnx_element_type: int) -> OrtValue:
         """
         This method creates an instance of OrtValue on top of the numpy array.
         No data copy is made and the lifespan of the resulting OrtValue should never
@@ -771,12 +800,14 @@ class OrtValue:
         when we want to use an ONNX data type that is not supported by numpy.
 
         :param data: numpy.ndarray.
-        :param onnx_elemenet_type: a valid onnx TensorProto::DataType enum value
+        :param onnx_element_type: a valid onnx TensorProto::DataType enum value
         """
-        return OrtValue(C.OrtValue.ortvalue_from_numpy_with_onnx_type(data, onnx_element_type), data)
+        return cls(C.OrtValue.ortvalue_from_numpy_with_onnx_type(data, onnx_element_type), data)
 
-    @staticmethod
-    def ortvalue_from_shape_and_type(shape, element_type, device_type: str = "cpu", device_id: int = 0):
+    @classmethod
+    def ortvalue_from_shape_and_type(
+        cls, shape: Sequence[int], element_type, device_type: str = "cpu", device_id: int = 0
+    ) -> OrtValue:
         """
         Factory method to construct an OrtValue (which holds a Tensor) from given shape and element_type
 
@@ -788,7 +819,7 @@ class OrtValue:
         # Integer for onnx element type (see https://onnx.ai/onnx/api/mapping.html).
         # This is helpful for some data type (like TensorProto.BFLOAT16) that is not available in numpy.
         if isinstance(element_type, int):
-            return OrtValue(
+            return cls(
                 C.OrtValue.ortvalue_from_shape_and_onnx_type(
                     shape,
                     element_type,
@@ -800,7 +831,7 @@ class OrtValue:
                 )
             )
 
-        return OrtValue(
+        return cls(
             C.OrtValue.ortvalue_from_shape_and_type(
                 shape,
                 element_type,
@@ -812,77 +843,77 @@ class OrtValue:
             )
         )
 
-    @staticmethod
-    def ort_value_from_sparse_tensor(sparse_tensor):
+    @classmethod
+    def ort_value_from_sparse_tensor(cls, sparse_tensor: SparseTensor) -> OrtValue:
         """
         The function will construct an OrtValue instance from a valid SparseTensor
         The new instance of OrtValue will assume the ownership of sparse_tensor
         """
-        return OrtValue(C.OrtValue.ort_value_from_sparse_tensor(sparse_tensor._get_c_tensor()))
+        return cls(C.OrtValue.ort_value_from_sparse_tensor(sparse_tensor._get_c_tensor()))
 
-    def as_sparse_tensor(self):
+    def as_sparse_tensor(self) -> SparseTensor:
         """
         The function will return SparseTensor contained in this OrtValue
         """
         return SparseTensor(self._ortvalue.as_sparse_tensor())
 
-    def data_ptr(self):
+    def data_ptr(self) -> int:
         """
         Returns the address of the first element in the OrtValue's data buffer
         """
         return self._ortvalue.data_ptr()
 
-    def device_name(self):
+    def device_name(self) -> str:
         """
         Returns the name of the device where the OrtValue's data buffer resides e.g. cpu, cuda, cann
         """
         return self._ortvalue.device_name().lower()
 
-    def shape(self):
+    def shape(self) -> Sequence[int]:
         """
         Returns the shape of the data in the OrtValue
         """
         return self._ortvalue.shape()
 
-    def data_type(self):
+    def data_type(self) -> str:
         """
-        Returns the data type of the data in the OrtValue
+        Returns the data type of the data in the OrtValue. E.g. 'tensor(int64)'
         """
         return self._ortvalue.data_type()
 
-    def element_type(self):
+    def element_type(self) -> int:
         """
         Returns the proto type of the data in the OrtValue
         if the OrtValue is a tensor.
         """
         return self._ortvalue.element_type()
 
-    def has_value(self):
+    def has_value(self) -> bool:
         """
         Returns True if the OrtValue corresponding to an
         optional type contains data, else returns False
         """
         return self._ortvalue.has_value()
 
-    def is_tensor(self):
+    def is_tensor(self) -> bool:
         """
         Returns True if the OrtValue contains a Tensor, else returns False
         """
         return self._ortvalue.is_tensor()
 
-    def is_sparse_tensor(self):
+    def is_sparse_tensor(self) -> bool:
         """
         Returns True if the OrtValue contains a SparseTensor, else returns False
         """
         return self._ortvalue.is_sparse_tensor()
 
-    def is_tensor_sequence(self):
+    def is_tensor_sequence(self) -> bool:
         """
         Returns True if the OrtValue contains a Tensor Sequence, else returns False
         """
         return self._ortvalue.is_tensor_sequence()
 
-    def numpy(self):
+    def numpy(self) -> np.ndarray:
         """
         Returns a Numpy object from the OrtValue.
         Valid only for OrtValues holding Tensors. Throws for OrtValues holding non-Tensors.
@@ -890,7 +921,7 @@ class OrtValue:
         """
         return self._ortvalue.numpy()
 
-    def update_inplace(self, np_arr):
+    def update_inplace(self, np_arr) -> None:
         """
         Update the OrtValue in place with a new Numpy array. The numpy contents
         are copied over to the device memory backing the OrtValue. It can be used
@@ -948,7 +979,7 @@ class SparseTensor:
     depending on the format
     """
 
-    def __init__(self, sparse_tensor):
+    def __init__(self, sparse_tensor: C.SparseTensor):
         """
         Internal constructor
         """
@@ -960,11 +991,17 @@ class SparseTensor:
                 "`Provided object` needs to be of type `onnxruntime.capi.onnxruntime_pybind11_state.SparseTensor`"
             )
 
-    def _get_c_tensor(self):
+    def _get_c_tensor(self) -> C.SparseTensor:
         return self._tensor
 
-    @staticmethod
-    def sparse_coo_from_numpy(dense_shape, values, coo_indices, ort_device):
+    @classmethod
+    def sparse_coo_from_numpy(
+        cls,
+        dense_shape: npt.NDArray[np.int64],
+        values: np.ndarray,
+        coo_indices: npt.NDArray[np.int64],
+        ort_device: OrtDevice,
+    ) -> SparseTensor:
         """
         Factory method to construct a SparseTensor in COO format from given arguments
 
@@ -985,12 +1022,17 @@ class SparseTensor:
         For strings and objects, it will create a copy of the arrays in CPU memory as ORT does not support those
         on other devices and their memory can not be mapped.
         """
-        return SparseTensor(
-            C.SparseTensor.sparse_coo_from_numpy(dense_shape, values, coo_indices, ort_device._get_c_device())
-        )
+        return cls(C.SparseTensor.sparse_coo_from_numpy(dense_shape, values, coo_indices, ort_device._get_c_device()))
 
-    @staticmethod
-    def sparse_csr_from_numpy(dense_shape, values, inner_indices, outer_indices, ort_device):
+    @classmethod
+    def sparse_csr_from_numpy(
+        cls,
+        dense_shape: npt.NDArray[np.int64],
+        values: np.ndarray,
+        inner_indices: npt.NDArray[np.int64],
+        outer_indices: npt.NDArray[np.int64],
+        ort_device: OrtDevice,
+    ) -> SparseTensor:
         """
         Factory method to construct a SparseTensor in CSR format from given arguments
 
@@ -1011,7 +1053,7 @@ class SparseTensor:
         For strings and objects, it will create a copy of the arrays in CPU memory as ORT does not support those
         on other devices and their memory can not be mapped.
         """
-        return SparseTensor(
+        return cls(
             C.SparseTensor.sparse_csr_from_numpy(
                 dense_shape,
                 values,
@@ -1021,7 +1063,7 @@ class SparseTensor:
             )
         )
 
-    def values(self):
+    def values(self) -> np.ndarray:
         """
         The method returns a numpy array that is backed by the native memory
         if the data type is numeric. Otherwise, the returned numpy array that contains
@@ -1093,19 +1135,19 @@ class SparseTensor:
         """
         return self._tensor.format
 
-    def dense_shape(self):
+    def dense_shape(self) -> npt.NDArray[np.int64]:
         """
         Returns a numpy array(int64) containing a dense shape of a sparse tensor
         """
         return self._tensor.dense_shape()
 
-    def data_type(self):
+    def data_type(self) -> str:
         """
         Returns a string data type of the data in the OrtValue
         """
         return self._tensor.data_type()
 
-    def device_name(self):
+    def device_name(self) -> str:
         """
         Returns the name of the device where the SparseTensor data buffers reside e.g. cpu, cuda
         """