onnxruntime/onnxruntime/python/torch_cpp_extensions/setup.py
Vincent Wang 5ecfaef042
ATen Fallback for Inference (#11597)
* aten op for inference

* fix build error

* more some code to training only

* remove domain from operator name

* move aten_op_executor ext out from ortmodule

* add pipeline

* add exec mode

* fix script

* fix ut script

* fix test pipeline

* failure test

* rollback

* bugfix

* resolve comments

* enable aten for python build only

* fix win build

* use target_compile_definitions

* support io binding

* turn off aten by default

* fix ut

Co-authored-by: Vincent Wang <weicwang@microsoft.com>
Co-authored-by: zhijxu <zhijxu@microsoft.com>
2022-06-09 16:07:30 +08:00

19 lines
668 B
Python

# -------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License.
# --------------------------------------------------------------------------
import os
from setuptools import setup
from torch.utils import cpp_extension
filename = os.path.join(os.path.dirname(__file__), "aten_op_executor/aten_op_executor.cc")
setup(
name="ort_torch_ext",
version="1.0",
ext_modules=[cpp_extension.CppExtension(name="ort_torch_ext.aten_op_executor", sources=[filename])],
packages=["ort_torch_ext"],
cmdclass={"build_ext": cpp_extension.BuildExtension},
)