Граф коммитов

532 Коммитов

Автор SHA1 Сообщение Дата
Wenbing Li 8153bc1a3a
Feature extraction C API for whipser model (#755)
* Feature extraction C API for whipser model

* Update the docs

* Update the docs2

* refine the code

* fix some issues

* fix the Linux build

* fix more data consistency issue

* More code refinements
2024-07-11 11:20:36 -07:00
cao lei 95d65e4ec0
sync to flash attention kernel 2.5.9 and add document of how to write custom op (#757)
* sync to flash attention kernel 2.5.9

* support users to overload GetMayInplace and ReleaseMayInplace

* Undo the change for pybind11 dependency
2024-07-10 07:09:40 -07:00
Wenbing Li b436d09459
Fix the CI pipeline for the latest PyTorch release. (#759) 2024-07-08 16:21:48 -07:00
Wenbing Li f1abea14e8
Update CMakeLists.txt (#754) 2024-06-25 11:12:21 -07:00
Chester Liu 0f1f454867
Fix C4459 warning in custom_op_lite.h (#751)
Internal workitem: https://task.ms/aii/29719

Co-authored-by: Xavier Dupré <xadupre@users.noreply.github.com>
2024-06-25 10:28:27 +08:00
Wenbing Li 3b275b16bc
Upgrade pybind11 2.12 to support both numpy 1.x and 2.x (#750) 2024-06-20 15:18:17 -07:00
Wenbing Li cbed8fd575
Add a generic image processor and its C API (#745)
* Add a generic image processor

* add more tests

* Fix the test failures

* Update runner.hpp
2024-06-20 10:53:49 -07:00
Chester Liu 58b552388f
Fix several C5038 warnings (#748) 2024-06-20 08:20:30 +08:00
Xavier Dupré bef5f07e33
Add custom ops ReplaceZero (#739)
* Add custom ops ReplaceZero

* fix merge conflicts
2024-06-18 11:36:14 +02:00
Xavier Dupré 05df33b302
Add missing documentation for fused kernels (#744) 2024-06-18 10:54:15 +02:00
Wenbing Li 2f9595af74
Fix the pipeline breaks dues to the MSVC 19.40 and numpy 2.0 release (#747)
* dd "-allow-unsupported-compiler" flags to Windows CUDA flags

inspired by this PR: https://github.com/microsoft/onnxruntime/pull/21004

* switch to cmake command line

* handle the issues caused by the latest MSVC release

* correct the typo

* correct the parameter

* try one dash again

* use the installed cmake

* use cmake standalone installation firstly

* use the standalone cmake in win32 python too

* fix it more

* one more try

* fix the MacOS pipeline issue

* fix the pip command line
2024-06-17 16:58:11 -07:00
Wenbing Li 3c22daa4cf
disable azure ops from ci/packaging pipelines (#746)
* disable azure ops from ci/packaging pipelines

* add the missed files

* keep the env variable flag

* add python to the path?
2024-06-13 21:11:55 -07:00
Xavier Dupré 690bed71b6
Add operator MulSigmoid, MulMulSigmoid (#741)
* Add operator MulSigmoid

* add mul mul sigmoid

* add comments

* Apply suggestions from code review

---------

Co-authored-by: Wei-Sheng Chin <wechi@microsoft.com>
2024-06-12 10:29:42 +02:00
Xavier Dupré f5055466d5
Add custom kernel ScatterNDOfShape (#705)
* first draft

* clang

* Draft for ScatterNFOfShape

* fix build

* disable test when cuda is missing

* fix implementation

* update test

* add MaskedScatterNdOfShape

* fix merge conflicts
2024-06-11 09:59:46 +02:00
Xavier Dupré 79f3b048d4
Add custom op Transpose2DCast (#737)
* Add custom op Transpose2DCast

* fix compilation issues

* fix compilation issues
2024-06-06 17:44:21 +02:00
Xavier Dupré 1e8c1211a5
Add custom kernels AddSharedInput, MulSharedInput (#734)
* Add custom kernel AddSharedInput, MulSharedInput

* fix compilation

* compilation issue

* fix unit test
2024-06-05 10:42:22 +02:00
Sayan Shaw c9bba37f91
update java packaging pipeline to have .pom and .jar files in correct location (#735)
Co-authored-by: Sayan Shaw <sayanshaw@microsoft.com>
2024-06-03 14:43:31 -07:00
Wenbing Li ca433cbea7
Refactor the unit tests and cmake build script (#726)
* refine the build script

* complete the unit tests.

* remove the commented code
2024-05-30 14:16:14 -07:00
Xavier Dupré b60df02fd0
Use of OrtxStatus in kernel NegXPlus1 (#732)
* first draft for NegXPlus1

* complete

* fix unit test

* rename one test

* remove test if not cuda

* switch to OrtxStatus

---------

Co-authored-by: Wenbing Li <10278425+wenbingl@users.noreply.github.com>
2024-05-30 10:56:06 +02:00
Xavier Dupré 95a49faabe
Add kernel NegXPlus1 = 1 - X (#709)
* first draft for NegXPlus1

* complete

* fix unit test

* rename one test

* remove test if not cuda

---------

Co-authored-by: Wenbing Li <10278425+wenbingl@users.noreply.github.com>
2024-05-29 15:26:44 +02:00
Wenbing Li 1eaf5caf56 Update onebranch-windows-build-stage.yml 2024-05-28 16:03:34 -07:00
Scott McKay a1285d8f36
Fix CG warnings. (#731)
- update protobuf version being used by sentencepiece and the java tests
- ignore unused language bindings from protobuf and triton
- specify the CG config file with ignored directories where required

Fix cgmanifest.json
- 'git' entries require a commit hash not version
- use 'other' for opencv third party code that is included directly in the opencv repo
  - the path isn't a valid repositoryUrl value to be provided as a 'git' entry
- update version numbers/commit hashes to match the latest code

Co-authored-by: Sayan Shaw <52221015+sayanshaw24@users.noreply.github.com>
2024-05-29 07:47:55 +10:00
Adam Pocock fcf28fe83a
Setting Java module name to com.microsoft.onnxruntime.extensions. (#730) 2024-05-28 19:58:39 +10:00
Wenbing Li a1e342acb9
Fix the Linux and MacOS wheel build for packaging issues (#727)
* Update wheels_macos.yml

* remove mulslinux support

* Update wheels_linux.yml

* Update wheels_linux.yml

* remove appcenter testing
2024-05-24 14:12:27 -07:00
Wenbing Li 474540d8a5
Fix the image processing output data discrepancy (#722)
* some data calc fixing

* Update image_transforms.hpp

* really split the images

* Update image_transforms.hpp
2024-05-20 12:44:48 -07:00
Wenbing Li c3c5f1cbb1
Remove C++ filesystem library dependency for the compatibility of old system (#721)
* Remove C++ filesystem library dependency for the compatibility of old OS.

* Update file_sys.h
2024-05-18 07:23:45 -07:00
Wenbing Li 97ee9eb56f
Refactor OrtxStatus to be header-only implmentation. (#720) 2024-05-17 15:40:11 -07:00
Tang, Cheng f0ef40d074
add move constructor and Release API for tensor (#717)
Co-authored-by: Cheng Tang <chenta@microsoft.com@onnxruntime-a10.bxgbzpva45kedp3rhbsbit4phb.jx.internal.cloudapp.net>
2024-05-17 11:50:20 -07:00
cao lei 3649db065d
Introduce ONNXRUNTIME_PKG_DIR parameter to pip install (#719)
* introduce ONNXRUNTIME_PKG_DIR parameter to pip install

* update document
2024-05-17 05:58:37 -07:00
Wenbing Li 4781a9d1d8
Add ci pipeline for pre-processing API testing (#718)
* Add ci pipeline for pre-processing API testing

* update cmake for testing

* add test cases back

* add other two pipelines

* fix macos pipeline
2024-05-16 15:39:52 -07:00
Wenbing Li 311dd35401
Add ImageProcessor for Multimodel model Pre-processing (#715)
* only keep the image decoder from opencv

* initial build

* refine the code

* Add clear functions

* Update CMakeLists.txt

* Update opencv.cmake

* change the output type to float

* get the result

* align image-process with original Python

* move the LoadRawImages into library

* fix the calculation error

* fix the pipeline build issue

* fix the build breaks in ci pipeline

* support json configuration file and refactor the code.
2024-05-15 14:35:14 -07:00
Scott McKay beb9fbbae2
Fix warnings (#713) 2024-05-13 10:14:37 +10:00
Baiju Meswani 660af0d79a
Return added_tokens_ by reference (#711) 2024-05-07 11:47:57 -07:00
Wenbing Li c58c930739
Ignore all streaming output of invalid utf-8 string (#704)
* Ignore all streaming output of invalid utf-8 string

* Update bpe_streaming.hpp

* add the phi-3 tokenizer test

* add a streaming test for phi-3 model

* fix the utf-8 validation

* fix the utf-8 validation 2

* fix the utf-8 validation 3

* fix the utf-8 validation 4
2024-05-06 16:46:55 -07:00
cao lei e645cdab8d
Introduce flash attention and cutlass library (#708)
* refactor cuda ops, remove contrib folder

* introduce flash attention and cutlass

* resolve comments

---------

Co-authored-by: Lei Cao <leca@microsoft.com@onnxruntime-a10.bxgbzpva45kedp3rhbsbit4phb.jx.internal.cloudapp.net>
2024-05-05 22:52:28 -07:00
cao lei dfdf52e759
refactor cuda ops, remove contrib folder (#707)
Co-authored-by: Lei Cao <leca@microsoft.com@onnxruntime-a10.bxgbzpva45kedp3rhbsbit4phb.jx.internal.cloudapp.net>
2024-05-03 12:18:59 -07:00
Wenbing Li 8645a846fb
A tutorial of build ort-extensions from source as a static library (#703)
* The tutorial of build from source as a static library

* update test flag control

* add the tutorial
2024-05-01 13:46:27 -07:00
Tang, Cheng 3b889fc42f
update custom op v2 struct to be able to invoke from eager mode (#700)
Co-authored-by: Cheng Tang <chenta@a100.crj0ad2y1kku1j4yxl4sj10o4e.gx.internal.cloudapp.net>
Co-authored-by: Wenbing Li <10278425+wenbingl@users.noreply.github.com>
2024-04-30 13:53:39 -07:00
Yi-Hong Lyu 0175f90216
Bump up version in main from 0.11.0 to 0.12.0 (#702)
Bump up version in main from 0.11.0 to 0.12.0 since the release branch has been cut.
2024-04-30 11:45:33 -07:00
Rachel Guo 3dfec76c10
Revert net7.0 update for now (#701)
* revert net 7.0 changes for now

* minor update

---------

Co-authored-by: rachguo <rachguo@rachguos-Mini.attlocal.net>
2024-04-29 21:40:56 -07:00
Wenbing Li a8bce4328b
Add the tokenizer C ABI (#693)
* initial checkins

* fix the selectedops build failures

* add the tokenization implementation

* update the windows DEF file for c abi in cmake file

* fix the build on linux

* fix some warnings and remove the unused code

* initial import of unit tests from tfmtok

* add streaming API support

* fix the merges loading issues

* complete export from tfmtok - needs input id fixing

* fix the unit test failures.

* fix all unit test failure

* refactor streaming code

* remove the unused code

---------

Co-authored-by: Sayan Shaw <sayanshaw@microsoft.com>
2024-04-29 16:45:49 -07:00
Tang, Cheng 1f31d33ed4
Eager mode: cuda kernel support (#694)
* add UT for neg_pos_cuda in eager mode and fix build break in Windows

* fix Linux build break

* adjust argument and path

* remove old cudaContext

* add ort cuda test back

* fix cuda tests

* undo debug code

* undo useless change

---------

Co-authored-by: jslhcl <jslhcl@gmail.com>
Co-authored-by: Cheng Tang <chenta@a100.crj0ad2y1kku1j4yxl4sj10o4e.gx.internal.cloudapp.net>
Co-authored-by: Sayan Shaw <52221015+sayanshaw24@users.noreply.github.com>
2024-04-24 12:49:00 -07:00
Rachel Guo 627e93ac08
fix version in renaming (#692)
Co-authored-by: rachguo <rachguo@rachguos-Mac-mini.local>
Co-authored-by: Wenbing Li <10278425+wenbingl@users.noreply.github.com>
2024-04-19 10:30:43 -07:00
Wenbing Li f9290e8bac
Add a status class for future tokenizer API implementation (#690)
* Add a status class for future API implementation

* Update bpe_kernels.cc

* fix the ios package pipeline

* update mistral test model name
2024-04-18 21:12:14 -07:00
Wenbing Li 646462790b
Refactor the header file directory and integrate the eager tensor implementation (#689)
* refactor the header file in include folder

* fix the basic-token eager unit test case

* a more flexible way to handle string tensor shape.

* fix the unit test path issue

* remove the multi-inherits to avoid issue during pointer casting

* add api cmake build support

* undo some temporary changes

* code refinement

* fix variadic arg

* only expose the context for ort version >= 17

* fix a shape bug

* fix the cuda build issue

* change ifdef condition of GetAllocator

* finalize the ort c abi wrapper file name

* fix the iOS build break

* align gtest version with triton

* Update ext_apple_framework.cmake for iOS header files

---------

Co-authored-by: Cheng Tang <chenta@a100.crj0ad2y1kku1j4yxl4sj10o4e.gx.internal.cloudapp.net>
2024-04-17 12:58:19 -07:00
Rachel Guo fe8cd9ee8d
Add extensions catalyst support (#684)
* save work

* add flags to disable build that's currently not supported on macabi

* update

* update

* fix arg type

* update ext_test.cmake

* fix

* try add flags

* exclude ext_test

* add missing downloading steps

* nameing minor fix

* update ios version etc.

* fix

* minor fix

* minor fix

* clean up

* nuget package changes for catalyst extensions (#686)

Co-authored-by: rachguo <rachguo@rachguos-Mini.attlocal.net>

* update to net7.0 and add help comments

---------

Co-authored-by: rachguo <rachguo@rachguos-Mac-mini.local>
Co-authored-by: rachguo <rachguo@rachguos-Mini.attlocal.net>
2024-04-17 10:43:35 -07:00
Wenbing Li a96ed42beb
Update ext_java.cmake (#688) 2024-04-10 16:22:12 -07:00
Wenbing Li 00a594f13d
Standardize the inputs for ONNX STFT op for Whisper model (#681)
* Standardize the inputs for ONNX STFT op for Whisper model

* undo the format change

* Update _torch_cvt.py
2024-03-29 11:13:30 -07:00
cao lei 5aefc7e54d
pass CMAKE_CUDA_ARCHITECTURE from command line (#683) 2024-03-28 15:08:36 -07:00
Wenbing Li 5d558bd34f
Refine the cuda build support (#680) 2024-03-27 10:08:07 -07:00