Commit graph

1025 commits

Author SHA1 Message Date
Ryan Hill
9ef92f352f Test Java pipeline fix 2021-05-19 16:33:55 -07:00
Ryan Hill
c569dee80a Merge branch 'master' of https://github.com/microsoft/onnxruntime into ryanunderhill/cuda_shared 2021-05-18 19:00:28 -07:00
Yulong Wang
077e8c6b40
allow update_version.py to update new npm packages (#7746)
* update versions for npm packages

* remove package-lock.json in list
2021-05-18 16:15:19 -07:00
Taewoo Kim
1e6ad669cf Support arm64e for osx
Add arm64e to choices variable
2021-05-18 14:58:58 -07:00
Changming Sun
26a472c948
Increase test timeout from 1 hour to 2 hours (#7735)
I saw a test timeout in our nodejs packaging pipeline. I'm not sure if it is because it ran slower than before or it's a deadlock issue. Increasing the timeout will be helpful for investigating such issues.
2021-05-18 10:51:58 -07:00
Ryan Hill
70f52251d9 Merge with master 2021-05-17 22:33:34 -07:00
Changming Sun
38d90b0f15
Cleanup install_deps.sh (#7734) 2021-05-17 19:27:47 -07:00
Jesse Benson
f977644324 ROCM support int reductions 2021-05-17 16:42:06 -07:00
Thiago Crepaldi
4fe2ffae16
Fix ORTModule python doc generation (#7704)
* Fix ORTModule python doc generation

* Address comment
2021-05-17 09:55:49 -07:00
Ryan Hill
67adb7bfe0 Merge with master 2021-05-16 18:41:57 -07:00
liqunfu
d604281a86
Liqun/training pkg to run tests (#7662) 2021-05-16 09:10:57 -07:00
liqunfu
3ead2f2f39
update pt lightning version (#7711)
Co-authored-by: liqun <liqun@OrtTrainingDev4.af05slrtruoetgaxwwjv5nsq5e.px.internal.cloudapp.net>
2021-05-15 21:46:16 -07:00
Yulong Wang
97d9bcd644
[js/web] fix bundle for multi-thread, add e2e test and support nodejs (#7688)
* fix bundle for multi-thread, add e2e test and support nodejs

* add copyright banner

* resolve comments

* add comments for isMultiThreadSupported()
2021-05-14 18:15:38 -07:00
Yulong Wang
c53b5be509
force multi steps to use the same commit in CI (#7697) 2021-05-14 15:13:38 -07:00
liqunfu
359fe1d197
Liqun/ort training version (#7620) 2021-05-14 09:54:19 -07:00
ashbhandare
56e993a434
Bump to rel-1.9.1 (#7684) 2021-05-13 18:41:28 -07:00
Ryan Hill
86cb70a118 Sync with Master 2021-05-12 21:28:07 -07:00
Vincent Wang
dac24f7d63
Add ATenOp and call aten::embedding and its Backward Op from ORT (#7590)
* build with libtorch and impl torchembedding

* fix op shape infer

* local commit

* atenfunctionop

* call aten operator from online extension

* rollback build.py

* resolve comments

* bugfix

* fix build

* fix ortmodule test

* remove external outputs, resolve comments

* resolve comments

* export embedding to microsoft::atenop

* bugfix
2021-05-13 09:24:27 +08:00
Guoyu Wang
a47a234b7e
Add minsdkver for AAR and AndroidTest (#7669) 2021-05-12 16:01:25 -07:00
Olivia Jain
29172d8f54
Setup EP Dashboard (#7321)
* setting up dashboard
* posting to ort dashboard
* creating separate docker file
* including common deps
* tracking latency over time
2021-05-11 10:33:39 -07:00
Guoyu Wang
ce8473a4ea
Add script to build fat iOS framework (#7607) 2021-05-11 09:46:24 -07:00
Scott McKay
d39db89fbb
Add info on some additional pytorch models that were added to the test models. No new operators are required. (#7644) 2021-05-11 19:48:28 +10:00
Guoyu Wang
69d1db83ac
Enable bitcode for iOS by default (#7640) 2021-05-10 21:27:45 -07:00
Ryan Hill
6076ef965b Training fix 2021-05-10 15:09:35 -07:00
Ryan Hill
912b61e490 Java fix for non cuda case 2021-05-10 13:02:56 -07:00
Ryan Hill
49a8b5db0f Fix minimal build 2021-05-10 11:33:04 -07:00
Ryan Hill
1698c57fcc Merge with master 2021-05-10 00:41:07 -07:00
Ryan Hill
64c0deeb7e Revert "Switch yml back to regular build pool"
This reverts commit be35fc2a5a.
2021-05-10 00:14:13 -07:00
Ryan Hill
be35fc2a5a Switch yml back to regular build pool 2021-05-09 10:48:58 -07:00
Hariharan Seshadri
4b691a5c0d
Add ability for memory arenas to "shrink" periodically (#7284) 2021-05-08 07:53:21 -07:00
Changming Sun
41e370c2b3
Update protobuf to 3.16 (#7616) 2021-05-07 14:09:23 -07:00
Ryan Hill
29288eb480 Java test on my VM 2021-05-06 17:01:50 -07:00
Ryan Hill
192d23060e Revert yml changes 2021-05-05 22:34:25 -07:00
Ryan Hill
8ba8c26233 Merge with master 2021-05-05 15:05:00 -07:00
Ryan Hill
401751b4c7 Merge with master 2021-05-05 15:01:02 -07:00
baijumeswani
f3a70f1aec
Ignore invalid input argument to install_os_deps.sh (#7566) 2021-05-05 14:33:31 -07:00
Changming Sun
a284eede64
Fix Linux CPU pipeline (#7584) 2021-05-05 13:26:10 -07:00
Sheil Kumar
91985ab03d
add use_dml (#7569)
Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
2021-05-05 08:55:13 -07:00
Rachel Guo
d8cf960412
Add android test app to validate Java API for ORT-Mobile Android (#7477)
* test

* [gwang] make cmake compile work

* [gwang] enble build apks

* some build update

* add simple sigmoid test android project and cmake

* add build.py

* refine and remove unused import lib

* address CR comments

* remove unnecessary files

* add README.md

* minor update

* remove

* minor change

* fix ci failure and minor update

* fix typo in project folder

* remove

* remove and minor update

* refine

* minor fix

* fix

* fix typo

* add gradle spotlessApply task to fix CI failure

* fix

* enable spotlessApply in build gradle

* revert some changes

* minor fix

* run spotless apply for format

* address CR comments and fix CI version and format

* refine

* Refine

* address comments

* refine

* refine

* modify

* reformat

* resolve version conflicts

* minor update

* minor update

* address comments

* minor update

Co-authored-by: Guoyu Wang <wanggy@outlook.com>
2021-05-04 15:39:14 -07:00
Guoyu Wang
e05528a365
Update Android AAR packaging pipeline script (#7559)
* update android package pipeline

* update shell script

* update script

* add kMSExperimentalDomain to reduction
2021-05-04 11:13:33 -07:00
Scott McKay
594dde2647
Validate that the conversion script from the python package can be used to convert models. (#7517) 2021-05-04 16:25:04 +10:00
George Wu
faea7a222d
linux trt package pipeline (#7537) 2021-05-03 19:14:20 -07:00
Ryan Hill
bc7f8ad4f8 Revert python version 2021-05-03 17:11:50 -07:00
Ryan Hill
edf0522b35 Point to RyanWinGPU 2021-05-03 16:38:26 -07:00
baijumeswani
cab84d902e
Install and use conda on ortmodule CI pipelines (#7530)
* Install and use conda on ortmodule CI pipelines

* Update build script to install onnxruntime wheel before running unit tests

* Remove python 3.5 from install_python_deps

* Pinning deepspeed version to 0.3.15
2021-05-03 15:52:22 -07:00
Scott McKay
830d9e54dd
Add script to dump initializer, NodeArg, Node and subgraph info from an ORT format model (#7516) 2021-05-04 08:34:35 +10:00
Yulong Wang
7079dfb93d
[wasm] fix and unify webassembly target name (#7549) 2021-05-03 10:37:25 -07:00
Sheil Kumar
94c4c44bfc
Enable Microsoft.Ai.MachineLearning package to work on .NET5 down to 17763 Windows SDK (#7522)
* upgrade cswinrt and downgrade target framework

* fix sdk version references

* cswinrt 1.1.0

Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
2021-05-01 00:56:36 -07:00
Tang, Cheng
54db6648af
kerne invoker api for eager mode (#7473)
* initial draft for kernel invoke api

* initial implementation of kernel invoker

* [eager] fix build on Mac

* [eager] increment input name in kernel invoker

* temp fix for type in eager mode

* use global default log manager

* rollback the previous commit since it break linux build

* Revert "rollback the previous commit since it break linux build"

This reverts commit 58c2c3423a.

* Eager Mode: fix linking on macOS

* optimizer_execution_frame: ignore unused lambda capture (model_path)

* fix link issue

* ORTInvoker: set correct input argument tensor element proto types

Do not set a type proto on output arguments to allow ORT to deduce them

* ORTInvoker: create only one logging manager

* Minor fix to set execution provider type correctly. (#7000)

Co-authored-by: Chandru Ramakrishnan <chandru-r@github.com>

* training fix

* support config output ml values in frame, so we can use it to implement inplace update

* Fix range loop error while building. (#7087)

Co-authored-by: Chandru Ramakrishnan <chandru-r@github.com>

* Conditionally link with nsync_cpp if not windows. (#7151)

Co-authored-by: Chandru Ramakrishnan <chandru-r@github.com>

* Fixed initialization order in ORT kernel invoker (#7342)

* Updated constructor of ort_kernel_invoker to take a logger.

* Changed linking order.

* Updated test.

* add inplace ut

* add build option

* Update include/onnxruntime/core/eager/ort_kernel_invoker.h

Co-authored-by: Derek Murray <Derek.Murray@microsoft.com>

* resolve comments in pr

* fix build break;merge from master

* fix build break

Co-authored-by: Cheng Tang <chenta@microsoft.com>
Co-authored-by: Aaron Bockover <abock@microsoft.com>
Co-authored-by: Chandru Ramakrishnan <41447659+chandru-r@users.noreply.github.com>
Co-authored-by: Chandru Ramakrishnan <chandru-r@github.com>
Co-authored-by: Derek Murray <Derek.Murray@microsoft.com>
2021-04-30 13:33:58 -07:00
Adrian Tsai
70e67ddd2b
Update DirectML version to 1.5.1 and enable ARM/ARM64 builds with DML (#7511)
* Update DirectML to version 1.5.1
* Enable --use_dml with ARM and ARM64
* Add ARM/ARM64 binaries to nuget packages
2021-04-30 00:49:30 -07:00