saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-06-29 03:30:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
7863 commits 2856 branches 57 tags 1.3 GiB
Commit graph

7863 commits

This branch
This branch
All branches
Author SHA1 Message Date
Sheil Kumar
71a1a7b471
Enable building winml with --build_nuget (#9632) 
* Enable building winml with --build_nuget

* Fix flake8 errors

* semicolor

Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
 2021-11-04 00:42:51 -07:00
Guoyu Wang
9cedb12c89
Add App Center e2e test to Android package (#9653) 
* Add app center test for Android pipeline

* update android test path

* Add logging of system abi

* fix java spotless error
 2021-11-03 22:56:46 -07:00
Chi Lo
c8151b4037
Add percentile method for PTQ (#9342) 
* Add percentile method for calibration

* Update configuration
 2021-11-03 22:18:51 -07:00
Changming Sun
2406a425a7
Move the common part of Windows CPU CI pipeline to a template file (#9650) 2021-11-03 17:35:51 -07:00
liqun Fu
15867dcc08
enable prefast check with orttraining win pipeline (#9638) 
* enable prefast check with orttraining win pipeline

* timeout to 200

Co-authored-by: liqun <liqun@OrtTrainingDev4.af05slrtruoetgaxwwjv5nsq5e.px.internal.cloudapp.net>
 2021-11-03 15:20:44 -07:00
Dmitri Smirnov
6ff02b04a8
Add Java build/test dependancies JUnit and Google Protobuf Java to cgmanifest (#9641) 
Add Java build/test dependancies JUnit and Google Protobuf Java
 2021-11-03 15:16:59 -07:00
baijumeswani
230099e482
Make ORTModule serializable (#9634) 2021-11-03 13:54:05 -07:00
Jeff Bloomfield
3a1b4045c9 Merge remote-tracking branch 'upstream/master' into DmlDev 2021-11-02 17:56:53 -07:00
Yufeng Li
51f84a0330
support quantization of empty tensor (#9640) 2021-11-02 16:35:23 -07:00
RandySheriffH
4644f8bc2c
refactor profiling logics (#9567) 
Co-authored-by: RandySheriffH <rashuai@microsoft.com>
 2021-11-02 14:31:39 -07:00
Ginés Hidalgo
19804876d9
Updated data_types.cc to avoid warning C4946 (#9611) 2021-11-01 22:03:50 -07:00
Weixing Zhang
e11fde0179
libonnxruntime_providers_rocm.so and libonnxruntime_providers_shared.so are not included in python package. (#9618) 
* libonnxruntime_providers_rocm.so and libonnxruntime_providers_shared.so are not included in python package.

Co-authored-by: Weixing Zhang <wezhan@microsoft.com>
 2021-11-01 19:12:09 -07:00
Ginés Hidalgo
020ec9c0f5
[DmlEp] Added missing include to DmlOperator.cpp to its own header (#9576) 
* Added missing include to DmlOperator.cpp to its own header
* Update DmlOperator.cpp
Followed @fdwr suggestion
 2021-11-01 18:15:36 -07:00
sumitsays
88f61a1b2d
[DmlEp] DmlEp acknowledges ORT_NO_EXCEPTIONS (#9622) 
* Make DmlEp Clang compatible for EPIC
* Fix build issues occurred when engine/lotus points to ORT Github latest
* Fix more build errors
* Fixed one build issue and removed temporary changes for Clang
* Addressed comments on the PR.
* [WIP] - DmlEp ORT NO Exception
* Made DmlEp compatible with ORT_NO_EXCEPTION
* Fixed typo
* Addressed comments on the PR, mostly nit styling and using approriate HR error code
* Added dependency of ErrorHandling.h
* Addressed comment on the PR
Co-authored-by: Sumit Agarwal <sumitagarwal@microsoft.com>
 2021-11-01 17:32:43 -07:00
Hariharan Seshadri
f41396eff0
Small addendum to #9624 (#9639) 2021-11-01 15:54:21 -07:00
Hariharan Seshadri
1240c595a9
Fix a couple of bugs with how memory pattern planning is enabled/disabled (#9624) 2021-11-01 10:24:41 -07:00
Ginés Hidalgo
c1112813e7
Added missing _In_ to ort_apis.h to be consistent with its cc file (#9557) 2021-11-01 10:10:26 -07:00
TomWildenhain-Microsoft
5247247b7f
Add Resize Handler for Transpose Optimizer and revise Layout Transformation API (#9607) 
* Add Resize Handler for Transpose Optimizer

* Add tests transpose optimizer tests for Resize op

* Fix typo

* Edit for Scott's comments

* Make helper functions static

* Change perm argument to const ref
 2021-10-31 23:51:11 -07:00
Yi-Hong Lyu
d203cdf132
Check output edges in QDQ (#9600) 2021-10-31 23:41:51 -07:00
Ginés Hidalgo
ccf1b8ad00
[DmlEp] Avoid warning C4495 (#9533) 
* Update MLOperatorAuthorImpl to remove warning C4495

Update MLOperatorAuthorImpl to remove warning C4495: nonstandard extension '__super' used: replace with explicit base class name

* Update DmlOperatorRecurentNeuralNetwork to avoid warning C4495

Update DmlOperatorRecurentNeuralNetwork to avoid warning C4495: nonstandard extension '__super' used: replace with explicit base class name
 2021-10-31 22:49:17 -07:00
Ginés Hidalgo
034f297884
[DmlEp] Avoided warning C4458: declaration of 'X' hides class member (#9583) 2021-10-31 20:05:44 -07:00
Edward Chen
c315d1b3cd
Always enable ORT format model loading. (#9586) 2021-11-01 10:00:08 +10:00
groenenboomj
5c56fa0def
Miopen conv grad (#9574) 
* Add source for conv_grad

* Add sources for ROCm EP.
* Transliterate sources for conv_grad for ROCm EP.

* Add conv_grad to ROCm EP

Add conv_grad to ROCm execution
provider.

* Update ROCm EP ConvGrad

Update ConvGrad for the ROCm EP to match other EP
changes and fix a build issue.
 2021-10-31 11:19:46 -07:00
Brian Martin
a07da457d1 Merged PR 6622182: add back change history that I lost with a squash commit 
Related work items: #36867798
 2021-10-30 20:06:26 +00:00
ISS Build Account
6a2d709db4 Merge remote-tracking branch 'upstream/master' into dmldev_temp 2021-10-30 13:04:27 -07:00
Brian Martin
6c236fd939 Merged PR 6622174: merge latest onnxruntime into dmldev 
there was a merge conflict in onnxruntime/core/providers/dml/OperatorAuthorHelper/Common.h that required manual merging.

Related work items: #36867798
 2021-10-30 19:59:33 +00:00
Ginés Hidalgo
79436a2d5b
Avoided warning C5038 (#9543) 
Updated several DML EP files to avoid warning C5038: data member 'member1' will be initialized after data member 'member2' / base class 'base_class'

More information:
https://docs.microsoft.com/en-us/cpp/error-messages/compiler-warnings/c5038?view=msvc-160
 2021-10-30 00:36:22 -07:00
Jingqiao Fu
a3e4d77b35
Replace wstring_convert with std::wstring (#9614) 
* remove wstring_convert

* .

* fix indentation
 2021-10-29 19:03:54 -07:00
Jingqiao Fu
f7774a91d6
Add api-ms-win-core-com-l1-1-0.dll, shlwapi.dll, oleaut32.dll to delay load (#9619) 2021-10-29 18:54:23 -07:00
Guoyu Wang
fa4658e8a9
Move to XCode new build system if building on Mac using XCode (#9617) 
* Use xcode new build system

* Address cr comments
 2021-10-29 18:44:55 -07:00
Guoyu Wang
57491b6f93
Add App Center test for iOS package (#9605) 
* Add app center test for iOS package

* fix flake8

* fix yml templates path

* Address CR comments
 2021-10-29 15:23:01 -07:00
Hariharan Seshadri
b5f7bb7d10
Update ONNX (#9462) 2021-10-29 10:33:40 -07:00
sumitsays
7744cc1013
[DmlEp] Make DmlEp compatible with Clang for EPIC (#9585) 
* Make DmlEp Clang compatible for EPIC

* Fix build issues occurred when engine/lotus points to ORT Github latest

* Fix more build errors

* Fixed one build issue and removed temporary changes for Clang

* Addressed comments on the PR.

* Style fixes

* Fix unreachable code

Co-authored-by: Sumit Agarwal <sumitagarwal@microsoft.com>
Co-authored-by: Dwayne Robinson <dwayner@microsoft.com>
 2021-10-29 03:19:35 -07:00
Scott McKay
eb2612b588
Remove netcoreapp2.1 target as it is EOL and out of support. Attempting to use it with VS now causes unit test run failures. (#9603) 2021-10-29 11:11:22 +10:00
Changming Sun
173e538b80 Update mac-ios-packaging-pipeline.yml 2021-10-28 14:25:29 -07:00
Changming Sun
cc73bcc243 Suppress component governance component warnings for ios 2021-10-28 14:25:29 -07:00
Ginés Hidalgo
1731f0080a
Update attention_cpu_base.h to suppress static analysis warning 2021-10-28 13:35:57 -07:00
Xavier Dupré
9c15c68ed4
Enable fallback when forward fails due to non contiguous tensor (#9369) 2021-10-28 13:04:54 -07:00
Tianlei Wu
a01a3f2552
Add more statistics in transformer profiler (#9578) 
* add statistics of cuda kernel
* grouping by provider + operator
* add --input to import profiling result
 2021-10-28 11:35:03 -07:00
Viswanath Boga
85874bb315
embed layer fusion gpt2 (#9336) 
* Changes to fuse embed layer for gpt2, kernal changes pending

* verified add output and regular add match

* Test added for additional output embedlayernorm, working on CUDA

* Test passing on CPU

* updated convert_to_onnx toll to check parity correctly

* removed some debugs

* couple of TODO left as in optimizer.py

* removed changes to optimizer.py

* fixing build

* fixing build

* updated order of initilization

* added a test case for float16

* updating the docs

* updating tests failing due to embed layer fusion

* update unit tests

* updating CUDA documentation in operatorkernels.md

* addressing comments

* OperatorKernels.md updated with CUDA

* adding TODO to qembed_layer

* minor edit

* updated docs

* addressing comments

* adding position ids to embed layer gpt2

* updating fused gpt2 model

* added extra test

* remove comments

* addressing comments

* contrib_defs.cc updated

* all tests passing

* fixing a typo

* minor edit

* trigger build

* qembedlayernorm checkinputs updated

* fixing build error

* fixing build error

* fixing build error
 2021-10-28 11:06:26 -07:00
Tianlei Wu
a555740708
Attention fusion: update uint8 tensor parsing for ONNX upgrade (#9564) 
* use UnpackTensor to parse uint8 tensor
* address review feedback
 2021-10-28 10:38:10 -07:00
Sunghoon
17cf39a964
Clean up unnecessary codes in softmax and hardmax kernel (#9580) 
* add p50 in test

* remove unnecessary codes from softmax

* remove unnecessary codes from hardmax

Co-authored-by: Yulong Wang <yulongw@microsoft.com>
 2021-10-28 10:01:46 -07:00
TomWildenhain-Microsoft
e8268c9a18
Add Transpose Optimizer and modify nhwc optimizer to use it. (#9284) 
* Add Transpose Optimizer and modify nhwc optimizer to use it.

* Fix casts

* Fix casts2

* Fix move

* Add tests

* Add headers

* Fixes and tests

* Remove explicit template instantiation

* Fix build warning

* Name unit tests

* Code review fixes

* Add some comments

* Fix some casts

* Make optimization slightly less agressive

* Some unit test fixes

* Update Attention pattern to work with transpose optimizer

* Update attention fuser

* Fix attention fusion python script

* Improve transpose optimizer documentation

* Create OptimizerCtx struct

* Disable Slice handler for testing

* Implement Slice int32

* Only push transposes leading up to other transposes

* Improve optimization heuristic

* Add exemption for MaxPool

* Document transpose optimizer api.h

* Revert fusion tests to master

* Remove temp files

* Replace typedef with using

* Trim trailing whitespace

* Move class declarations from api_impl.h to api_impl.cc

* Remove copy constructors and move allocator

* Alphabetize headers

* Add override keyword

* Comments for nhwc_transformer

* Rename OrtGraph to ApiGraph, etc.

* Wrap line

* Remove extra qualifier on ApiGraph

* Refector attention fusion

* Remove c-style casts from api_impl.cc

* Improve documentation

* Avoid printing vector in ORT_ENSURES

* Revert attention fusion refactor

* Remove duplicate cost heuristics and improve documentation

* Fix size_t casts

* Fixes from Scott's review

* Unrevert attention refactor and more updates from Scott's review

* Revert api_impl.cc ValueInfo change

* only optimize first transpose input

* Unrevert api_impl.cc changes

* Make vector call reserve

* transpose_optimizer.cc update from Scott's comments

* Rename api::Graph to api::GraphRef etc.

* Consider domains 'onnx.ai' and '' equal

* Replace AddInput with SetInput

* Improve tests

* quantization and heuristic tests

* Comments for tests

* Replace const string_view with string_view and update tests

* Fixes requested by Edward

* Fix std::string to string_view conversion

* Add <string> to includes

* Fix bug for broadcasting ops with unknown rank. Slight safety improvements

* Changes requested by Edward

* Fix formatting

* Improve description of cost metric
 2021-10-27 22:10:39 -07:00
Changming Sun
87b1fddd97
Add Linux/MacOS ARM64 support to nuget packaging pipeline (#9570) 2021-10-27 19:00:43 -07:00
Ginés Hidalgo
2d44bd525b
DML functions always returning a value (#9485) 
* Always return a value
* @fdwr advice added
 2021-10-27 15:21:32 -07:00
Sheil Kumar
8dd4d207e2 Merged PR 6606929: RI 10/26 from github into fork #2 
Related work items: #36831318
 2021-10-27 21:56:14 +00:00
Scott McKay
a2b3e6bb23
Remove pointless assert. (#9571) 2021-10-28 07:33:40 +10:00
Dmitri Smirnov
4e76360261
Prevent PySparseTensor form being garbage collected if we have an outstanding OrtValue (#9540) 
Prevent PySparseTensor form being garbage collected if we have an outstanding OrtValue
  Improve  comments.
 2021-10-27 11:28:37 -07:00
Changming Sun
aa76520e60
Update macOS build agents to macOS 11 (#9562) 2021-10-27 10:00:04 -07:00
Thiago Crepaldi
5d5c03bcdc
Fix opset version change by not using copy of global constant (#9393) 2021-10-27 12:42:06 -04:00