Граф коммитов

13 Коммитов

Автор SHA1 Сообщение Дата
Wenbing Li 19fcc4dc1c
clean up the deprecated warnings from pytest (#542) 2023-08-28 10:09:08 -07:00
Wenbing Li 1af7a56b28
update Python pipelines for release (#353)
* re-enable Python pipelines

* deprecate the direct setup.py call

* pipeline fixing

* run cmake from visual studio

* remove the self check

* support different ort versions

* remove ort 1.9 and add 1.13

* ci pipeline fixing

* fix the test with latest pytorch

* code refinement

* torch version detection

* make package python version more consistent.
2023-02-06 18:23:56 -08:00
shaahji a7deb7b52c Update CI build workflow matrix
Upgraded the onnxruntime headers from v1.6 to v1.9

Update workflow matrix so it's consistent across the platforms and using
newer versions of the dependencies. Current supported matrix -

+------------+------------------------+-----------------------+-----------------------+----------------------+
|Python      |           3.7          |           3.8         |            3.9        |          3.10        |
+------------+------------------------+-----------------------+-----------------------+----------------------+
|Onnxruntime |  1.9.0 (Sept 22, 2021) | 1.10.0 (Dec 7, 2021)  | 1.11.0 (Mar 26, 2022) | 1.12.1 (Aug 4, 2022) |
|Torch       |  1.9.1 (Sept 22, 2021) | 1.10.0 (Oct 21, 2021) | 1.11.0 (Mar 10, 2022) | 1.12.1 (Aug 5, 2022) |
|TorchVision | 0.10.1 (Jun 15, 2021)  | 0.11.1 (Oct 21, 2021) | 0.12.0 (Mar 10, 2022) | 0.13.1 (Aug 5, 2022) |
|TorchAudio  |  0.9.0 (Jun 15, 2021)  | 0.10.0 (Oct 21, 2021) | 0.11.0 (Mar 10, 2022) | 0.12.1 (Aug 5, 2022) |
+------------+------------------------+-----------------------+-----------------------+----------------------+

Release versions strictly follow the convention of onnxruntime being one
release ahead of all its dependencies.
2022-09-02 23:05:58 -07:00
Wenbing Li 292a0297b4
reformat test code and verify the pipeline (#251)
* reformat test code and verify the pipeline

* upgrade googletest version

* fix the merge issue

* more formating
2022-06-20 12:38:06 -07:00
Wenbing Li 6c3b496e3f
Support the domain name in the PyOp. (#136) 2021-08-26 11:04:45 -07:00
Wenbing Li a428be447c
optimize the gpt2-bs model after the generation (#119) 2021-07-08 15:36:11 -07:00
Wenbing Li fd1216b027
fix some build and env issues. (#111) 2021-06-10 09:57:49 -07:00
Wenbing Li 3806e29421
rename the package to onnxruntime_extensions (#92)
* rename the package to onnxruntime_extensions

* fix the cmake file
2021-05-12 12:02:57 -07:00
Wenbing Li 2243847f22
The GPT-2 post processing code end-to-end example (#86)
* Support the tensor renaming for the embedded graph

* Add ORT verifying step in the conversion.

* make the gpt-e2e work

* Support the loop in mytorch

* gpt2 end-to-end works

* Polish the code and fix the unit test.
2021-04-28 10:56:30 -07:00
Wenbing Li aa846c3116
Support the pre/post processing Python and pytorch code snippets to be converted and be merged into the ONNX model. (#76)
* initial checkins

* restructure the implementation.

* refine the Python interface

* Finalize the interface.

* Add the custmop class for the customization.

* Test the eager_op with vector_to_string customop

* Refine the customop conversion interface.

* initial onnx builder

* Runable with incorrect result.

* reformat the onnx_ops calls

* a few of operators working on tracing

* handcraft all op conversion

* Add the unit testing for mytorch

* unit test passed.

* Add some documents...

* Move non-torch API into onnxruntime_customops.utils module.

* Fix the unit test issues.

* Fix some typos.
2021-03-12 10:39:21 -08:00
Wenbing Li b5ba84a185
Add hook feature for the model debugging. (#62)
* Add hook feature for the model debugging.

* use the dynamic noode name

* default as floating

* typo

* skip on macos

* add documents
2021-02-10 11:02:06 -08:00
Wenbing Li 2dfd95e64b
rename the package name to onnxruntime-customops (#36)
* normalize the root package name in Python

* fixing build on Linux

* update the tutorial as well
2020-12-22 20:16:30 -08:00
Xavier Dupré 3ef90b4628
Refactoring, split C++ custom operators into multiple files, add C++ unit test (#8)
* refactoring
* remove useless include
* remove pragma once from cc files
* add custom_op_test.onnx
* remove unnecessary imports, add header in project file, run C++ unit tests
2020-11-03 16:54:06 +01:00