Commit graph

2113 commits

Author SHA1 Message Date
Kyle
10bdf6e797
Fix Maven Sha256 Checksum Issue (#22600)
### Description
<!-- Describe your changes. -->
**Changes applied to maven related signing:** 
* Windows sha256 file encoded by utf8(no BOM)
* powershell script task used latest version, previous 5.1 version only
supports utf8 with BOM.
* Windows sha256 file content in format 'sha256value
*filename.extension'.
* Linux sha256 file content in format 'sha256value *filename.extension'.

**More information about powershell encoding:**
Windows powershell encoding reference: [about_Character_Encoding -
PowerShell | Microsoft
Learn](https://learn.microsoft.com/en-us/powershell/module/microsoft.powershell.core/about/about_character_encoding?view=powershell-7.4)
- for version 5.1, it only has 'UTF8 Uses UTF-8 (with BOM).'
- for version v7.1 and higher, it has:
     utf8: Encodes in UTF-8 format (no BOM).
     utf8BOM: Encodes in UTF-8 format with Byte Order Mark (BOM)
     utf8NoBOM: Encodes in UTF-8 format without Byte Order Mark (BOM)
2024-10-25 08:13:02 -07:00
Jian Chen
3fe7aa3b59
Adding new Python package testing pipeline for Cuda Alt (#22584)
### Description
<!-- Describe your changes. -->



### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2024-10-24 19:24:53 -07:00
Changming Sun
15556c492d
Use a private PIP feed in 1ES pipeline (#22590) 2024-10-24 19:10:30 -07:00
Scott McKay
b9903617b6
Exclude padding section from minimal build size report (#22578)
### Description
<!-- Describe your changes. -->
Should make the binary size report more stable as changes < 4K can occur
when a padding boundary is crossed.


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2024-10-25 08:14:15 +10:00
Jian Chen
3ae7c3c0a6
Enable 1ES on Python CUDA Package Pipelines (#22560)
### Description
These 3 following CUDA packaging pipeline shoud be enabled with 1ES
after this pull request.
•
[Python-CUDA-Packaging-Pipeline](https://dev.azure.com/aiinfra/Lotus/_build?definitionId=1299&view=runs)
• [Python CUDA Alt Packaging
Pipeline](https://dev.azure.com/aiinfra/Lotus/_build?definitionId=1626)
• [Python DML Packaging
Pipeline](https://dev.azure.com/aiinfra/Lotus/_build?definitionId=1625)

This should also fix the issue where [Python packaging
pipeline](https://aiinfra.visualstudio.com/Lotus/_build?definitionId=841&_a=summary)
failed due to cannot find `publish_symbols`


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2024-10-24 09:51:00 -07:00
Kyle
70be2eb6da
Migrate Nuget Windows AI Pipeline to Use 1ES Template (#22572) 2024-10-24 09:15:39 -07:00
Yulong Wang
ef7f1ce08b
Update Node.js version from 18.x to 20.x in CI pipelines (#22576) 2024-10-24 07:34:42 -07:00
Kyle
d9ca84ef96
Add DoEsrp Check for Signature Verification (#22570)
### Description
<!-- Describe your changes. -->
Add DoEsrp Check for Signature Verification


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2024-10-24 16:55:36 +08:00
Changming Sun
a25c9315ea
Move ORT Training pipeline to github actions (#22543)
Move ORT Training pipeline to github actions and enable CodeQL scan for the code(including inference code).
We will move all pull request pipelines to Github Actions.
2024-10-23 11:57:15 -07:00
Jian Chen
ffaddead0a
Refactor cuda packaging pipeline (#22542)
### Description
<!-- Describe your changes. -->



### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2024-10-23 08:14:10 -07:00
Tianlei Wu
8a04ab421d
[CUDA] upgrade opencv in stable diffusion demo (#22470)
### Description
(1) Upgrade opencv
(2) Add some comments about onnxruntime-gpu installation

### Motivation and Context
opencv-python was locked to an older version, which has security
vulnerabilities: see https://github.com/microsoft/onnxruntime/pull/22445
for more info
2024-10-21 23:20:49 -07:00
Changming Sun
c7138a2630
Update CMake (#22516)
This pull request upgrades the CMake version from v3.31.0-rc1 to
v3.31.0-rc2 to include a bug fix for CUDA
https://gitlab.kitware.com/cmake/cmake/-/merge_requests/9902 from Nvidia
company.

AB#51692
2024-10-21 07:51:05 -07:00
kailums
3174e3da57
update pipline python version from 3.8 to 3.12 (#22517)
### Description
As the python3.8 is going to reach EOL. 

https://discuss.python.org/t/python-3-13-0-final-has-been-released/
https://discuss.python.org/t/python-3-8-is-now-officially-eol/66983

we update our ci pipeline python version which still using 3.8 to 3.12
2024-10-21 07:50:31 -07:00
Edward Chen
7964d3aef6
Specify iOS simulator runtime version (#22474)
- Allow specification of iOS simulator runtime version to use.
- Pick simulator runtime version (iphonesimulator 16.4) that is supported by the Xcode version (14.3.1) that we use.
- Disable CoreML EP's DepthToSpace op support for CoreML version less than 7, with DCR mode, and FP16 input. It doesn't produce the correct output in this case.
- Some cleanup of iOS test infrastructure.
2024-10-18 09:26:06 -07:00
Yulong Wang
1247d69c28
Add onnxtestdata cache for win-web-multi-browsers pipeline (#22477)
### Description

Apply onnxtestdata cache to win-web-multi-browsers pipeline

Same change that applied to win-web-ci #16659
2024-10-17 12:03:29 -07:00
Hector Li
ac98bcae37
Update QNN default version to 2.27 in CI pipeline (#22471)
### Description
Update QNN default version to 2.27 in CI pipeline
2024-10-16 22:05:47 -07:00
Changming Sun
f9e623e4d1
Update CMake to 3.31.0rc1 (#22433)
To include a bug fix:
https://gitlab.kitware.com/cmake/cmake/-/merge_requests/9890

Discussion:

https://discourse.cmake.org/t/cmake-incorrectly-links-to-nvrtc-builtins/12723/4

This bug fix should be included in our upcoming release, because right
now our GPU package depends on “libnvrtc-builtins.so.12.2" which has a
hardcoded CUDA version: 12.2. The minor CUDA version should not be
there.
2024-10-16 11:50:13 -07:00
Caroline Zhu
691de83892
Enable BrowserStack tests (#22457)
### Description
BrowserStack account issues have been resolved -- this PR enables E2E
browserstack tests in the pipeline again
2024-10-16 11:10:12 -07:00
PeixuanZuo
bf604428aa
[ROCm] Update ROCm Nuget pipeline to ROCm 6.2 (#22461)
1. Update ROCm Nuget pipeline build version to ROCm 6.2
2. Update AMD-GPU Agent Pool base docker image for ROCm Nuget pipeline
test stage. search `AMD GPU pipeline Nuget` page in onenote to see how
to update it.

passed pipeline:
https://aiinfra.visualstudio.com/Lotus/_build/results?buildId=580846&view=results
2024-10-16 10:36:49 -07:00
Jian Chen
af00a20f8a
Change ORT nightly python packages' name (#22450)
### Description
Our nightly CPU python package's name is "ort-nightly" instead of
"onnxruntime". It was because of some historical reasons. Tensorflow was
like that.
Now we would prefer to make them the same.
Do this change for all nightly python packages, including CPU,
GPU(CUDA), and maybe others.


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2024-10-15 18:44:59 -07:00
Caroline Zhu
6407d81b35
Disable BrowserStack testing stage (#22438)
### Description
We are seeing this [packaging
pipeline](https://aiinfra.visualstudio.com/Lotus/_build?definitionId=940&_a=summary)
fail because we are running into BrowserStack account issues. Disabling
this step until issues are resolved
2024-10-15 13:27:05 -07:00
Changming Sun
4af593a722
Add python 3.13 support (#22380)
1. Add python 3.13 to our python packaging pipelines
2. Because numpy 2.0.0 doesn't support thread free python, this PR also
upgrades numpy to the latest
3. Delete some unused files.
2024-10-14 18:07:54 -07:00
Yi Zhang
72cc72cc21
New rocm nuget publish pipeline (#22418)
### Description
Add a new pipeline to publish ROCM package to ADO



### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

### Test Link
https://dev.azure.com/aiinfra/Lotus/_build?definitionId=1615
2024-10-13 08:30:06 +08:00
Edward Chen
d7367653ab
Remove clean_docker_image_cache.py and clean-build-docker-image-cache-pipeline.yml. (#22409)
Clean up old script and build definition.
2024-10-11 14:25:13 -07:00
Kyle
cdebf37105
Add Digital Signature to DLLs in Maven Build (#22401)
### Description
* Add digital signature to dll files in jar files.
* Jar file names: onnxruntime-{version}.jar,
onnxruntime_gpu-{version}.jar

### Motivation and Context
#19204
2024-10-11 12:14:03 -07:00
sheetalarkadam
c06ecd415c
RC releases to Maven for Android (#22391)
### Description
Aallows alpha, beta and rc version releases to Maven for Android
artifacts.



### Motivation and Context
Helpful to release rc versions or test artifacts to Maven for testing.
For example, a new QNN android package is being released and it will be
nice to test the RC version for dependencies before release

## Future Work
Allow RC version for all Maven artifacts.
2024-10-11 08:58:02 -07:00
sheetalarkadam
dd2ea8469e
Add qnn android package (#22296)
### Description
Pre built QNN Android package


### Future Work
1. Setting up CI with Browserstack- onnxruntime_tests and Android test
2. ESRP Release to Maven
2024-10-10 10:37:22 -07:00
Changming Sun
2bef89c171
Upgrade absl to the latest released version (#22365)
### Description
Resolve #21976 .  
 
ABSL generally does not have forward/backward compatibility. Our code is
only compatible with one fixed LTS version. So it's important to fix the
version number there when using find_package to detect an installed
version.
2024-10-09 20:21:40 -07:00
Changming Sun
dcf1e0c3b0
Re-enable CUDA 12 python package test pipeline (#22370)
### Description
It runs after "Python-CUDA-Packaging-Pipeline" that runs on a CPU
machine that skipped all tests.
This testing pipeline is for doing the tests.
2024-10-09 20:21:27 -07:00
Hector Li
3b00024b55
Fix the QNN nuget package issue (#22358)
Fix the QNN nuget package issue

### Description
Inside the package, folder name \runtimes\win-arm64\ was changed to \runtimes\win-ARM64\, which breaks lib copy settings in Microsoft.ML.OnnxRuntime.QNN.props.


### Motivation and Context
Fix issue: https://github.com/microsoft/onnxruntime/issues/21692
2024-10-09 08:41:23 -07:00
Changming Sun
9ee963110e
Update manylinux version (#22355)
### Description
Update the commit from 59600894a2c1c18290944b83e989bfe618975230 to
1887322ed36d522409a6b805d4e7942cf76a8e40


### Motivation and Context
The new one has python 3.13.

AB#50959
2024-10-08 23:11:11 -07:00
Yulong Wang
c5d28cac4d
Initial WebGPU EP checkin (#22318)
### Description

This change introduces the WebGPU EP into ONNX Runtime.

To make the PR as simple as possible, this PR excluded the following:
- C API changes for WebGPU EP
- actual implementation of WebGPU EP. Currently in this PR, WebGPU is a
stub implementation that does not register any kernel.
- Python IO Binding update
- Node.js IO Binding update

This PR now contains only 43 file changes (while the working branch
contains 130+) and hopefully this makes it easier to review.

There is going to be separated PRs for each mentioned above.

Current working branch: #21904
2024-10-08 16:10:46 -07:00
Changming Sun
d98340968e
Stop publishing python 3.8/3.9 packages (#22343)
### Description
1. Stop publishing python 3.8/3.9 packages, to align with numpy. 
2. Add a trigger for CUDA12's python test pipeline.
2024-10-08 09:50:05 -07:00
Changming Sun
715b74d61a
Re-enable codesign for maven packages (#22308)
### Description
PR #22217 was reverted.  This PR re-enables it.


### Motivation and Context
2024-10-04 14:30:17 -07:00
Tianlei Wu
f3f33bfa05
Upgrade cutlass to 3.5.1 and cudnn frontend to 1.7.0 (#22316)
### Description
Upgrade cutlass to 3.5.1
Upgrade cudnn_frontend to 1.7.0
2024-10-04 11:48:50 -07:00
jingyanwangms
bb0c1f0a05
Update cuda version in release pipeline (#22305)
### Description
With TensorRT 10.4 update, the name of TensorRT windows package changed


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2024-10-03 22:28:28 -07:00
Caroline Zhu
c73e6afa6c
Migrate Android Java E2E tests from App Center to Browserstack (#22117)
### Description
- removed installing AppCenter + pipeline step that runs AppCenter
Espresso tests
- added script for running AppCenter tests

### Motivation and Context
App Center is getting deprecated in the next year + we have upcoming
Android work that depends on working E2E testing.

---------

Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
2024-10-02 15:04:58 -07:00
Edward Chen
c24e55b1f1
[Java] Add API for appending QNN EP (#22208)
- Add Java API for appending QNN EP
- Update Java unit test setup
  - Fix issues with setting system properties for tests
  - Unify Windows/non-Windows setup to simplify
2024-10-01 10:18:04 -07:00
Yufeng Li
96e9c99dce
remove neural-speed (#22236)
### Description
<!-- Describe your changes. -->
NS is not developed anymore and ORT doesn't use it for int4 inference
either. Remove it to clean up the code


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2024-10-01 09:50:44 -07:00
Scott McKay
ee7081b828
Fix syntax for some CoreML ML Program supported operator entries (#22268)
### Description
<!-- Describe your changes. -->
Fix syntax so usability checker works as expected.

### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2024-10-01 15:49:43 +10:00
Jian Chen
40bcb7664d
Revert "Jar Maven Signing - GnuPG and sha256" (#22273)
Reverts microsoft/onnxruntime#22217
2024-09-30 15:07:59 -07:00
Yi Zhang
d069475a63
Make A100 jobs in PR checks again (#22261)
### Description
if the variable is 1, the job running on A100 in PR checks.
Fixes
[AB#50333](https://aiinfra.visualstudio.com/6a833879-cd9b-44a4-a9de-adc2d818f13c/_workitems/edit/50333)


### Motivation and Context
We wish more big models which need to run on A100 can be tested in PR
checks, but Azure may decommission A100 agents without notifications
sometimes, which will block merging PRs.
This PR is an improvement of current workaround, making those jobs only
run main branch.
Once we find the A100 are all decommisioned by Azure, we could change
the UseA100 variable to 0 to disable the A100 jobs in PR checks
2024-09-30 08:29:30 -07:00
wejoncy
2cfe1f031d
[CoreML MLProgram] Support Float16 (1/N) (#22068)
### Description
Support Float16 for CoreML MLProgram EP.
Operations:
    "Add", "Mul", "Sub", "Div", "Pow", "Sqrt", "Reciprocal",
"Sigmoid", "Tanh", "Relu", "LeakyRelu", "Concat", "GridSample",
"GlobalAveragePool",
    "Clip", "DepthToSpace", "Resize", "Slice", "Conv",
    "ConvTranspose", "GlobalMaxPool", "Gemm", "MatMul",
    "AveragePool", "MaxPool", "Reshape", "Split", "Transpose"

### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

---------

Co-authored-by: Scott McKay <skottmckay@gmail.com>
2024-09-30 17:56:47 +08:00
Kyle
b81e76b9a6
Jar Maven Signing - GnuPG and sha256 (#22217)
### Description
<!-- Describe your changes. -->
Jar maven signing: 
- GnuPG 
- sha256.

Jar packages artifacts: 
- onnxruntime-android-full-aar
- onnxruntime-java
- onnxruntime-java-gpu


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
Previously, it is manually signed. 
Goal: make it automatically.
2024-09-27 17:50:06 +08:00
jingyanwangms
d0b0ecfdb9
[Running CI] Update TensorRT to 10.4 (#22049)
### Description
TensorRT 10.4 is GA now, update to 10.4



### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2024-09-26 11:10:52 -07:00
Dmitri Smirnov
a7c9f27d2d
Remove training pipelines from Win CPI CI as redundant (#22190) 2024-09-23 18:15:41 -07:00
Yi Zhang
8d2d40781c
set CMAKE_SYSTEM_PROCESSOR in xnnpack.cmake (#22155)
### Description
<!-- Describe your changes. -->



### Motivation and Context
By default, CMAKE_SYSTEM_PROCESSOR is same CMAKE_HOST_SYSTEM_PROCESSOR
https://cmake.org/cmake/help/latest/variable/CMAKE_SYSTEM_PROCESSOR.html
KleidiAI uses CMAKE_SYSTEM_PROCESSOR to determine whether to include
some arm64 ukernels.
https://gitlab.arm.com/kleidi/kleidiai/-/blob/main/CMakeLists.txt#L134
We use Mac with Intel CPU to cross compile MAC with ARM in ios packaging
pipeline
So we need to make CMAKE_SYSTEM_PROCESSOR same with ORT_TARGET_PROCESSOR
2024-09-20 15:19:26 -07:00
George Wu
944d87381d
[QNN EP] set up py packaging pipeline for Linux x64 (#22132)
set up a pipeline to produce nightly Linux x64 whls for onnxruntime-qnn
this can be used for offline context binary generation.
2024-09-18 23:24:32 -07:00
Yi Zhang
560778fd07
use mac 12 for esrp code sign (#22134)
### Description
Fix regression caused by #17361 



### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2024-09-19 12:06:41 +08:00
Adrian Lizarraga
b8dae685e4
[QNN EP] Build Python 3.12 wheel for Windows ARM64 (#22118)
### Description
Builds arm64 python 3.12 wheel for QNN EP.


### Motivation and Context
2024-09-17 21:16:31 -07:00