Commit graph

8730 commits

Author SHA1 Message Date
Changming Sun
ddaaeeab42
Disable a test in attention_op_test_helper.cc (#16054)
### Description
Disable a test in attention_op_test_helper.cc to make python packaging
pipeline pass.
2023-05-23 16:42:29 -07:00
RandySheriffH
ae2395cb56
Cherry-pick the fix to build rel-1.15 python package for AzureEP (#16044)
Cherry-pick the fix to build python package for AzureEP.

Co-authored-by: Randy Shuai <rashuai@microsoft.com>
2023-05-23 10:11:47 -07:00
Changming Sun
ade58cf789
Cherry-pick 4 commits to rel-1.15.0 branch (#16021)
### Description

Cherry-pick 4 commits to rel-1.15.0 branch

#14834 
#15727
#16010
#16011
2023-05-19 21:48:21 -07:00
Changming Sun
6cdf071a94
Cherry-picks to the release branch (#16017)
### Description
Cherry-picks 26 commits to the release branch. 
Most cherry-picks are clean merges. Except:

1. When I got conflicts in cgmanifest.json and download-deps.yml, I
choose to ignore the conflicts and regenerate the two files
2. There were some conflicts in cmake/deps.txt, onnxruntime_c_api.cc


PR list:

[js/webgpu] fix Transpose with non-float tensor (#15819)
[js/web] fix terser reserved symbols for worker (#15864)
[JSEP] fix constructor for OrtDevice (#15805)
Bump engine.io from 6.4.1 to 6.4.2 in /js/web (#15799)
Bump engine.io from 6.4.0 to 6.4.2 in /onnxruntime/test/wasm (#15798)
[wasm] revert emsdk to v3.1.19 (#15793)
[wasm/JSEP] add threaded build to artifacts (#15777)
[js/web] add target ort.webgpu.min.js (#15780)
update ort extensions to 94142d8391c9791ec71c38336436319a2d4ac7a0 (#15688)
fix: setting builder optimization level to TRT 8.6 default (#15897)
Adust GetVersionString() GetBuildInfoString() signatures and move them to OrtApi (#15921)
Fix segfault for multiple GPU run (regression) (#15823)
android package fix (#15999)
[CoreML EP] Minor changes to allow CoreML EP to handle more nodes and models. (#15993)
Adding support for conv fp16 fusion on Resnet50v1 (#15474)
update onnx release 1.14 for docker files (#15680)
Avoid generating training documentation during packaging (#15795)
Update Conv-Add-Relu Fusion Transformation (#15834)
Fix symbolic shape infer empty value_info (#15842)
NhwcFusedConv: Add before Activation (#15837)
use __hmul2 instead of __hmul2_rn (#15852)
change the EP device to default OrtDevice() for memoryType equals CPU Input (#15903)
Fixing NhwcFusedConv fp16 (#15950)
fix topo sort in quantization tool (#16003)
[doc] add LeakyRelu to coreml supported ops (#15944)
[DML EP] Add frequent upload heap flushing (#15960)

Co-authored-by: Yulong Wang 
Co-authored-by: dependabot[bot] 
Co-authored-by: Guenther Schmuelling 
Co-authored-by: Shalva Mist 
Co-authored-by: Maximilian Müller 
Co-authored-by: Dmitri Smirnov 
Co-authored-by: pengwa 
Co-authored-by: Ashwini Khade 
Co-authored-by: Edward Chen 
Co-authored-by: Jian Chen 
Co-authored-by: liqun Fu 
Co-authored-by: Baiju Meswani 
Co-authored-by: Tianlei Wu 
Co-authored-by: Chen Fu 
Co-authored-by: Ye Wang 
Co-authored-by: cao lei 
Co-authored-by: Yufeng Li 
Co-authored-by: Rachel Guo 
Co-authored-by: Patrice Vignola
2023-05-19 14:04:43 -07:00
Changming Sun
0f3aa9dd54
Add a comma to cgmanifest.json (#15998)
### Description
In PR https://github.com/microsoft/onnxruntime/pull/15797, the author
manually edited the cgmanifests/generated/cgmanifest.json file and made
an error there that makes the file ill formed.
2023-05-18 17:30:43 -07:00
RandySheriffH
a3febf979a
Cherry-pick azure ep for nuget (#15941)
Cherry pick a commit that can:

1. support for openAi audio endpoints;
2. package as nuget

This is for 1.15 AzureEP RC release.

---------

Co-authored-by: Randy Shuai <rashuai@microsoft.com>
2023-05-16 13:01:24 -07:00
Changming Sun
2fd1aea33b
Cherry-pick some PRs to the release branch (#15913)
### Description

Cherry-pick the following PRs to the release branch
https://github.com/microsoft/onnxruntime/pull/15858
https://github.com/microsoft/onnxruntime/pull/15807
https://github.com/microsoft/onnxruntime/pull/15816
https://github.com/microsoft/onnxruntime/pull/15775
https://github.com/microsoft/onnxruntime/pull/15779


They are all clean merges. 


---------

Co-authored-by: cloudhan <guangyunhan@microsoft.com>
Co-authored-by: Sumit Agarwal <sumitagarwal330@gmail.com>
Co-authored-by: RandySheriffH <48490400+RandySheriffH@users.noreply.github.com>
Co-authored-by: Randy Shuai <rashuai@microsoft.com>
2023-05-12 08:33:01 -07:00
Nat Kershaw (MSFT)
6ef420ec74
Add RC version missing cherry pick (#15920) 2023-05-12 05:36:00 -07:00
Linnea May
bf50a37fc9
User/linneamay/roi align 16 (#15812) (#15896)
### Description
<!-- Describe your changes. -->
Add registration for DML RoiAlign-16 and tests for new
coordinate_transform_mode attribute. PR
[7354](https://github.com/microsoft/onnxruntime/pull/7354) is still open
to fix the CPU EP version, which is why there are skipped tests right
now. That will be completed separately so that, for now, we can
officially support opset16 with the next release.


### 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. -->

---------

### 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. -->

Co-authored-by: Linnea May <linneamay@microsoft.com>
Co-authored-by: Dwayne Robinson <dwayner@microsoft.com>
2023-05-11 10:48:30 -07:00
Nat Kershaw (MSFT)
ed46afd7e1
Fix release version suffix for RC builds (#15865) (#15901)
Cherry pick nuget RC version changes from main

(cherry picked from commit 36c9ae0f58)
2023-05-11 09:19:43 -07:00
Sheil Kumar
96de9fe355
Cherry-Pick 2b7f26af7c: Add GridSample implementation to DirectML (#15788) (#15828)
Cherry-Pick 2b7f26af7c:
https://github.com/microsoft/onnxruntime/pull/15788

Add GridSample implementation to DirectML EP.
Temporary add HLSL shader in the DirectML EP to handle GridSample until
officially added to DirectML.
2023-05-08 10:47:15 -07:00
Jian Chen
abdd4f518a
Update TRT Windows Cuda 11.6 to 11.8 (#15746)
### Description
Update TRT Windows cuda 11.6 to 11.8



### Motivation and Context
We are adapting newer version of cuda systemwide.
2023-05-02 12:23:13 -07:00
Changming Sun
328cabb194
Download protoc from Github Release instead of Nuget (#15731)
### Description
Download protoc from Github Release instead of Nuget to avoid having
dependency on nuget.exe on Linux

### Motivation and Context
To avoid having dependency on nuget.exe on Linux. Many users' build
environment do not have nuget or dotnet.
2023-05-02 12:18:59 -07:00
Nat Kershaw (MSFT)
e901cdbf54
Add wildcard paths to the API docs generation workflows (#15313) 2023-05-02 10:43:45 -07:00
Chen Fu
4b8025e492
Parallelize fp16 pooling operators (#15766)
### Description
Parallelize fp16 pooling operators


### 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. -->
2023-05-02 08:48:56 -07:00
Chen Fu
bc58fd5413
fix compilation error in no absl build (#15769)
### Description

Fix no-absl build error:
2023-05-02 08:20:49 -07:00
Sohaib Iftikhar
92309187b3
Allow compilation using clang when using cuda. (#15672)
### Description
Currently compiling with clang + cuda leads to:

```
/code/build/_deps/onnxruntime-src/include/onnxruntime/core/common/make_string.h:33:6: error: call to function 'operator<<' that is neither visible in the template definition nor found by argument-dependent lookup
  ss << t;
     ^
/code/build/_deps/onnxruntime-src/include/onnxruntime/core/common/make_string.h:39:3: note: in instantiation of function template specialization 'onnxruntime::detail::MakeStringImpl<gsl::span<const long, 18446744073709551615>>' requested here
  MakeStringImpl(ss, args...);
  ^
/code/build/_deps/onnxruntime-src/include/onnxruntime/core/common/make_string.h:46:3: note: in instantiation of function template specialization 'onnxruntime::detail::MakeStringImpl<const char *, gsl::span<const long, 18446744073709551615>>' requested here
  MakeStringImpl(ss, args...);
  ^
/code/build/_deps/onnxruntime-src/include/onnxruntime/core/common/make_string.h:93:18: note: in instantiation of function template specialization 'onnxruntime::detail::MakeStringImpl<const char *, gsl::span<const long, 18446744073709551615>>' requested here
  return detail::MakeStringImpl(detail::if_char_array_make_ptr_t<Args const&>(args)...);
                 ^
/code/build/_deps/onnxruntime-src/onnxruntime/contrib_ops/cuda/quantization/qordered_ops/qordered_qdq.cc:73:12: note: in instantiation of function template specialization 'onnxruntime::MakeString<char[39], gsl::span<const long, 18446744073709551615>>' requested here
    return ORT_MAKE_STATUS(ONNXRUNTIME, INVALID_ARGUMENT, "Shape not meet clean tile requirement!", dims);
           ^
/code/build/_deps/onnxruntime-src/include/onnxruntime/core/common/common.h:188:48: note: expanded from macro 'ORT_MAKE_STATUS'
                                ::onnxruntime::MakeString(__VA_ARGS__))
                                               ^
/code/build/_deps/onnxruntime-src/include/onnxruntime/core/framework/tensor_shape.h:201:15: note: 'operator<<' should be declared prior to the call site or in namespace 'gsl'
std::ostream& operator<<(std::ostream& out, const TensorShape& shape);
              ^
1 error generated.
```
2023-05-02 01:12:39 -07:00
Changming Sun
034698cf6a
Revert "Implement lite custom op API (#15590)" (#15768)
This reverts commit cdf4fc49fc because it
breaks the "debug_node_input_output" build in "Post Merge" pipeline
2023-05-02 01:10:10 -07:00
Prathik Rao
090312af71
add local state dict option (#15759)
### Description

Adds an option to load local state dictionary for whisper model export.

### Motivation and Context

This is useful to demonstrate workflow of using ORT Training to get
model weights, downloading said weights onto a local gpu-enabled device,
exporting the custom model using `convert_to_onnx.py`, and then nicely
feeding the .onnx file into ORT InferenceSession.
2023-05-01 22:08:11 -07:00
Ye Wang
391f897983
Bring back SLN cuda kernel and use provider options to switch to standard implementation (#15660) 2023-05-01 18:35:26 -07:00
Nat Kershaw (MSFT)
9219615471
Fix python AP docs generation (#15760)
Docs are failing on the operator generation step. Remove this
temporarily so that we can publish.
2023-05-01 18:31:59 -07:00
Changming Sun
5352f6d9b0
Make "--cuda_version" build arg optional (#15758)
### Description
This change will allow us building CUDA EP without installing CUDA SDK
on Windows.

### Motivation and Context
Nvidia's CUDA installer comes with a VS extension. In the past, we
require installing the extension. It is a little bit inconvenient since:
1. Visual Studio must be installed before CUDA SDK. CUDA's installer
will not install the extension if your machine doesn't have Visual
Studio.
2. We need to install CUDA SDK on our build machines, instead of just
downloading it and using it.

After this change, we will not need to install CUDA SDK on our build
machines. So it will be easier to add a support for a different CUDA
version.

Also, fix two PreFast warnings.
2023-05-01 18:00:47 -07:00
Ye Wang
7f293d065a
Remove some D2D memcpy in T5 BeamSearch (#15706)
### Description
<!-- Describe your changes. -->

replace D2D memcpy with cuda kernels in creating decoder initial feeds
before:

![image](https://user-images.githubusercontent.com/52801275/234746326-209110e3-1cd4-4e8c-a488-515dd34c06c7.png)


after:

![image](https://user-images.githubusercontent.com/52801275/234736352-0bd027a0-e382-47d7-a1c5-ae9fbc9f1c9d.png)


### 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: Ubuntu <wy@v100-2.0cdb2e52twzevn1i4fi45bylyg.jx.internal.cloudapp.net>
2023-05-01 13:03:21 -07:00
Ashwini Khade
0ffae8073b
Creating Nuget and Android packages for Training (#15712)
### Description
This PR creates Nuget and Android for Training. 


### Motivation and Context
These packages are intended to be released in ORT 1.15 to enable
On-Device Training Scenarios.

## Packaging Story for Learning On The Edge Release
### Nuget Packages:
1. New Native package -> **Microsoft.ML.OnnxRuntime.Training** (Native
package will contain binaries for: win-x86, win-x64, win-arm, win-arm64,
linux-x64, linux-arm64, android)
2. C# bindings will be added to existing package ->
**Microsoft.ML.OnnxRuntime.Managed**

### Android Package published to Maven:
1. New package for training (full build) ->
**onnxruntime-training-android-full-aar**

### Python Package published to PyPi:
1. Python bindings and offline tooling will be added to the existing ort
training package -> **onnxruntime-training**
2023-05-01 12:59:56 -07:00
Sumit Agarwal
4c4f688a93
[DML EP] Fix dml_external_project (#15656)
### Description
While building ORT for DML EP with `dml_EXTERNAL_PROJECT` flag, 2
variables (`DML_SHARED_LIB`, `DML_PACKAGE_DIR`) value is not set
properly.



### 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. -->
2023-05-01 12:02:56 -07:00
liqun Fu
62fc6ed5a8
[Feature Request] Support Resize opset 19 (#15633) 2023-05-01 10:49:17 -07:00
cao lei
d58fa9805b
ExecutionProvider API refactor - replace OrtMemoryInfo with OrtDevice (#15618)
### Description
ExecutionProvider API refactor - replace OrtMemoryInfo with OrtDevice



### Motivation and Context
Currently “Location” is represented as ORTMemoryInfo, which is OrtDevice
+ OrtMemType, while OrtDevice is represent as DeviceType + DeviceId +
MemType. As we can see there is some unnecessary hierarchy, the proposal
is to make it a clear definition that to use OrtDevice as an abstraction
for Location

---------

Co-authored-by: Lei Cao <leca@microsoft.com>
2023-05-01 10:06:00 -07:00
Baiju Meswani
bb33285ec2
C# training api updates for on device training (#15720) 2023-05-01 10:01:38 -07:00
shalvamist
c10a6a9d17
Tensor <--> image - Adding per channel compute for Norm mean & Bias (#14705)
### Description
Enabled the use of per channel Bias and Mean normalization when converting an image <--> tensor.
Added a few bug fixes and updates to the relevant E2E tests.

---------

Co-authored-by: shalvamist <shalva.mist@microsoft.com>
2023-05-01 09:37:50 -07:00
Scott McKay
0770cf3699
Remove C# SessionOptions.RegisterCustomOpsUsingFunction. (#15754)
Symbol visibility from DllImport is inconsistent across platforms resulting in the symbol not necessarily being visible to ORT native code that tries to look it up by name.

Best solution is to use DllImport to load the library and to call the registration function directly. That requires the native SessionOptions handle and OrtApiBase struct. We could either make those public, or provide a helper where the user passes in a delegate from their DllImport. Can add when needed.
2023-05-01 09:14:21 -07:00
RandySheriffH
cdf4fc49fc
Implement lite custom op API (#15590)
Implement a set of new APIs for lightweight custom ops registration, to
save efforts on schema-composing.
A few highlights:

1. Support build-time type inference;
2. Support function-as-op for "stateless" ops;
3. Support structure-as-op for "stateful" ops;
4. Support varied input/output forms such as span, scalar, and tensors,
either optional or non-optional.

---------

Co-authored-by: Randy Shuai <rashuai@microsoft.com>
2023-05-01 08:45:26 -07:00
Chen Fu
0e9472d391
NHWC graph optimizer (#15724)
### Description

Augment nhwc graph optimizer to accommodate fp16 operators.


### Motivation and Context

With new fp16 conv operator added. This operator prefers NHWC data
layout. We need to augment existing graph optimizers to better utilize
the new operator.
2023-05-01 08:44:07 -07:00
Chunye Wang@AMD
d35850c142
[VitisAI]Update VitisAI EP to be compatible with VitisAI 3.5 (#15673)
### Description

Originally VitisAI EP only works with old version of VitisAI release. 


### Motivation and Context

Update VitisAI EP so that it works together with the current VitisiAI
3.5 and further version of VitisAI. We try our best to make it forward
compatible.

---------

Co-authored-by: Wang Chunye <chunywan@xilinx.com>
Co-authored-by: mingyue <mingyue@amd.com>
Co-authored-by: mingyueliuh <131847423+mingyueliuh@users.noreply.github.com>
Co-authored-by: liumingyue <mingyue@xilinx.com>
Co-authored-by: moore-ch <129165652+moore-ch@users.noreply.github.com>
Co-authored-by: shoucair <shoucai.ren@amd.com>
Co-authored-by: zz002 <zhenze.wang@amd.com>
Co-authored-by: BoarQing <yuz75@Pitt.edu>
Co-authored-by: Yueqing Zhang <yueqingz@amd.com>
Co-authored-by: Scott McKay <Scott.McKay@microsoft.com>
2023-05-01 08:28:26 -07:00
Jeff Bloomfield
3df3a85114
Default kOrtSessionOptionsDisableQuantQDQ to 1 when the DML EP is registered (#15725)
This addresses a performance regression in some INT8 models with the
DirectML EP by defaulting OrtSessionOptionsDisableQuantQDQ to 1 when the
EP is registered.

This regression occured due to the introduction of the QDQ propagation
transformer, which is based on this session option. That transformer
maximizes the number of nodes which are executed as quantized by
logically propagating quantize operators upstream and dequantize
operators downstream. However, it does this simply by inserting QDQ
pairs, with an expectation that something will recognize sequences of
DQ->Op->Q. This logic and related L2 transformers are not currently
enabled for the DirectML EP.

This change also removes a noisy warning when the session option for
memory pattern is overriden as the DirectML EP is registered.
2023-05-01 08:26:03 -07:00
Tianlei Wu
10dff4f665
only add type info from symbolic shape inference for fp16 conversion (#15617)
### Description

Walkaround of https://github.com/microsoft/onnxruntime/issues/15521.


### 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. -->
2023-04-30 23:22:11 -07:00
Chi Lo
6e652d0554
Support explicit TRT profiles from provider options (#15546)
Previous behavior of TRT EP to set TRT optimization profiles for dynamic
shape input is based on input tensor values. Users can't explicitly
specify the profiles.

This PR makes users capable of specifying min/max/opt profiles through
newly added three provider options:

`trt_profile_min_shapes`, `trt_profile_max_shapes` and
`trt_profile_opt_shapes`
with the format of "input1:dim1xdim2...,input2:dim3xdim4...".
(Note: It's similar to --minShapes, --maxShapes and --optShapes of
trtexec command-line
[flags](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#trtexec-flags))

For example, if you are using onnxruntime_perf_test, you can try this:

`./onnxruntime_perf_test -e tensorrt -r 1 -i
"trt_profile_min_shapes|imgs:1x3x384x288
trt_profile_max_shapes|imgs:32x3x384x288
trt_profile_opt_shapes|imgs:16x3x384x288" your_model_path`

If the engine cache is enabled, you still need to provide these three
explicit provider options in order to use this feature. ORT TRT will
compare the min/max/opt profile shape with the ones saved in .profile
file to decide whether to rebuild the engine.

Constraints to use these provider options: (1) Need to specify
min/max/opt profile shapes for all the dynamic shape input

 

This feature is also requested by other users:
https://github.com/microsoft/onnxruntime/issues/13851
2023-04-30 22:30:26 -07:00
Scott McKay
31e7d3d7d4
Disable TestRegisterCustomOpsWithFunction on Linux (#15747)
### Description
<!-- Describe your changes. -->
Disable new test that is failing on linux. Not required for this
release. Will fix in the next week.

Marshal.Prelink can be used on Windows to make the symbol available but
Linux appears to work differently.
Also need to update the pre-checkin tests so this is tested early as
it's only failing in the E2E tests run in the packaging pipeline.

### 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. -->
Fix packaging pipeline error.
2023-04-30 14:39:02 +10:00
Changming Sun
176161348e
Revert "make nuget workflow easy to debug. (#15693)" (#15744)
This reverts commit 53ff50d19a because it
make the nuget pipeline fail.
2023-04-29 19:05:01 -07:00
kunal-vaishnavi
7ae01cec15
Update wheel path to Whisper custom export script (#15739)
### Description
This PR updates the documentation for using the Whisper custom export
scripts via the wheel.



### Motivation and Context
The path should say
`onnxruntime.transformers.models.whisper.convert_to_onnx` instead of
`onnxruntime.transformers.models.convert_to_onnx`.
2023-04-29 17:32:34 -07:00
sfatimar
4fbc08e3c2
VPUX config fix and dynamic_shape bug fixed. (#15737)
Dynamic shapes was not working with serialized model so we are switching
to compile model method

### Motivation and Context
Dynamic shapes was not working with serialized model 
- If it fixes an open issue, please link to the issue here. -->

Signed-off-by: MaajidKhan <n.maajid.khan@intel.com>
Co-authored-by: MaajidKhan <n.maajid.khan@intel.com>
2023-04-29 15:48:34 -07:00
Adrian Lizarraga
d32c540b2d
[QNN EP] Support LRN operator (#15741)
### Description
Adds support for the LRN operator to QNN EP.

### Motivation and Context
Enables basic models like googlenet and alexnet to run entirely on QNN
EP.
2023-04-29 13:23:42 -07:00
Changming Sun
65020d433e
Prefast fixes for CUDA EP (#15726)
### Description
1. Adjust cmake flags. Do not modify CMAKE_CXX_FLAGS globally. Only
apply the flags to ORT code.
2. Fix some SDL warnings.
2023-04-29 12:43:12 -07:00
Jian Chen
ec2f038c6d
Update Nuget pipeline's Linux CUDA job to cuda 11.8 (#15516)
### Description
Fixed AB#14497
2023-04-29 07:38:18 -07:00
Rachel Guo
c8bd34f975
[js/rn] Package dependency change to manage ort-extensions for react_native app (#15641)
### Description
<!-- Describe your changes. -->

js/react_native package dependency change to manage ort-extensions for
react-native app.

Enable optional inclusion of ort-ext aar/ ort-ext pods for react-native
extensions apps when specifiy `ortExtensionsEnabled` in user's
package.json file


### 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: rachguo <rachguo@rachguos-Mac-mini.local>
Co-authored-by: rachguo <rachguo@rachguos-Mini.attlocal.net>
2023-04-29 00:07:12 -07:00
Yuhong Guo
41dcf0d32e
Expose build information in dynamic lib (#15643)
### Description
<!-- Describe your changes. -->
1. Add Build Info API to onnx.
2. Fix compile error while building onnxruntime_benchmark in MacOs.


### 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. -->
1. When Onnxruntime lib is serving online, we need a way to detect how
this lib is built. This PR helps the developer to get the build
information using `strings` such as git branch, git commit id, build
type and cmake cxx flags, which is showed as follows.


![image](https://user-images.githubusercontent.com/19584326/233794371-b2f95a2c-27fb-4709-a6dd-bf4bb12b0b5b.png)


![image](https://user-images.githubusercontent.com/19584326/233794360-f96f5d2e-332c-405c-83f1-370ccc2b86f8.png)

If the build env has no git, there will be no git related infor:


![image](https://user-images.githubusercontent.com/19584326/234558596-298c1b01-9a90-41bf-9372-7259a8f8e5be.png)


3. Fix the following compile error while building benchmark in MacOs.

![image](https://user-images.githubusercontent.com/19584326/233793571-c261ac1f-47b2-434d-a293-7e9edc6c8a66.png)

---------

Co-authored-by: Yuhong Guo <yuhong.gyh@antgroup.com>
2023-04-28 21:57:31 -07:00
Adrian Lizarraga
191deb4235
[QNN EP] Nuget package (#15711)
Adds pipeline for QNN NuGet package (x64 and arm64).
2023-04-28 19:33:14 -07:00
Rachel Guo
6a6091a519
[rn] Add support for loading model from buffer on iOS (#13802)
### Description
<!-- Describe your changes. -->

-Add support for loading model from buffer on iOS
-Update OnnxruntimeModuleTest to use updated loadModelFromBuffer
Based on #12676

### 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. -->

Issue: #12500

---------

Co-authored-by: rachguo <rachguo@rachguos-Mini.attlocal.net>
Co-authored-by: rachguo <rachguo@rachguos-Mac-mini.local>
2023-04-28 17:34:26 -07:00
kunal-vaishnavi
fe1ddd7b61
Fix bug when adding Whisper to wheel (#15708)
### Description
This PR adds `onnxruntime.transformers.models.whisper` to the wheel.

### Usage
There is a README.md document that shows sample commands. The following
command will show how to use the custom Whisper export script in more
detail.
```
$ python3 -m onnxruntime.transformers.models.whisper.convert_to_onnx --help
```

### Motivation and Context
This fixes an issue with adding the Whisper custom export scripts to the
wheel. The Whisper folder now appears in the wheel.
![Screenshot 2023-04-26
143705](https://user-images.githubusercontent.com/115581922/234708587-6d1b7d34-71a9-4f9f-a491-657ceb25afcb.jpg)
2023-04-28 16:03:55 -07:00
liqun Fu
2802c547a1
update OnnxMl.cs (#15702) 2023-04-28 11:20:29 -07:00
pengwa
29d13cea42
Cumulative update on optimizers and tests (on-device training) (#15499) 2023-04-28 09:55:39 -07:00