onnxruntime/csharp
Changming Sun ff1e446d00
ONNX Runtime 1.15.1 release (#16365)
### Description
The patch release will fix the following issues:
1. A coding problem in test/shared_lib/test_inference.cc that it should
use ASSERT_NEAR to test float values instead of ASSERT_EQ. Without this
change, some DNNL/OpenVino tests would fail on some AMD CPUs.
2. A misaligned error in cublasGemmBatchedHelper function. The error
only occurs when the GPU's CUDA Compute capability >=80. (In other
words: with TensorFloat-32 support)
3. A build issue that build with onnxruntime_ENABLE_MEMORY_PROFILE was
broken in 1.15.0 release.
4. Native onnxruntime library not loading in Azure App Service. It is
because in 1.15.0 we introduced a Windows API call to
SetThreadDescription. Though the API is available in all Windows 10
versions, some sandbox environments block using the API.
5. An alignment problem for xnnpack EP on Intel/AMD CPUs on PC
platforms.
6. Some training header files were missing in the 1.15.0 training NuGet
package.
7. Some fields in OrtCUDAProviderOptionsV2 struct are not initialized.


---------
Co-authored-by: cao lei <jslhcl@gmail.com>
Co-authored-by: Lei Cao <leca@microsoft.com>
Co-authored-by: Scott McKay <skottmckay@gmail.com>
Co-authored-by: Baiju Meswani <bmeswani@microsoft.com>
Co-authored-by: JiCheng <wejoncy@163.com>
Co-authored-by: Yuriy Chernyshov <thegeorg@yandex-team.com>
Co-authored-by: Artur <artur@vaadin.com>
Co-authored-by: Dale Phurrough <dale@hidale.com>
Co-authored-by: Yi Zhang <zhanyi@microsoft.com>
2023-06-15 15:45:21 -07:00
..
ApiDocs Lint updates csharp docs (#12962) 2022-09-14 17:56:41 -05:00
sample Add csharp docfx (#12596) 2022-08-25 09:51:32 -05:00
src ONNX Runtime 1.15.1 release (#16365) 2023-06-15 15:45:21 -07:00
test Cherry-picks to the release branch (#16017) 2023-05-19 14:04:43 -07:00
testdata Format all python files under onnxruntime with black and isort (#11324) 2022-04-26 09:35:16 -07:00
tools/Microsoft.ML.OnnxRuntime.PerfTool update OnnxMl.cs (#15702) 2023-04-28 11:20:29 -07:00
.clang-format
Directory.Build.props.in Patch Protobuf and ONNX's cmake files and enforce BinSkim check (#13694) 2022-11-18 10:09:47 -08:00
Nuget.CSharp.config
OnnxRuntime.CSharp.proj Add RC version missing cherry pick (#15920) 2023-05-12 05:36:00 -07:00
OnnxRuntime.CSharp.sln Add csharp docfx (#12596) 2022-08-25 09:51:32 -05:00
OnnxRuntime.DesktopOnly.CSharp.sln
OnnxRuntime.snk
readme.md Add .net6 support to the C# nuget package. (#11908) 2022-06-22 08:08:24 +10:00
readme.txt

ORT C# Managed Library

The solution files here are used to produce nuget packages for the C# bindings.

Note that the project naming is currently confusing and needs updating.

  • The Microsoft.ML.OnnxRuntime project produces the Microsoft.ML.OnnxRuntime.Managed nuget package.
  • The Microsoft.ML.OnnxRuntime nuget package contains the native (i.e. C++) code for various platforms.

Solution files

The main solution file is OnnxRuntime.CSharp.sln. This includes desktop and Xamarin mobile projects. OnnxRuntime.DesktopOnly.CSharp.sln is a copy of that with all the mobile projects removed. This is due to there being no way to selectively exclude a csproj from the sln if Xamarin isn't available.

If changes are required, either update the main solution first and copy the relevant changes across, or copy the entire file and remove the mobile projects (anything with iOS, Android or Droid in the name).

Development setup:

Requirements:

NOTE: The usage of this solution is primarily for ORT developers creating the managed Microsoft.ML.OnnxRuntime.Managed nuget package. Due to that, the requirements are quite specific.

Visual Studio 2022 v17.2.4 or later, with Xamarin workloads

There's no good way to use Visual Studio 2022 17.3 Preview in a CI, so we currently have to build pre-.net6 targets using VS, and .net6 targets using dotnet. We can't build them all using dotnet as the xamarin targets require msbuild. We can't package them using dotnet as that also requires msbuild.

Once the official VS 2022 release supports .net6 and is available in the CI we can revert to the original simple setup of building everything using msbuild.

To test packaging locally you will also need nuget.exe. Download from https://www.nuget.org/downloads. Put in a folder (e.g. C:\Program Files (x86)\NuGet). Add that folder to your PATH.

Magic incantations to build the nuget managed package locally:

If we're starting with VS 2022 17.2.4 we should have dotnet sdk 6.0.301

Make sure all the required workloads are installed dotnet workload install android ios maccatalyst macos - original example from here: - dotnet workload install android ios maccatalyst macos maui --source https://aka.ms/dotnet6/nuget/index.json --source https://api.nuget.org/v3/index.json - don't need 'maui' in this list until we update the sample/test apps - didn't seem to need --source arg/s for local build. YMMV.

Build pre-net6 targets msbuild -t:restore .\src\Microsoft.ML.OnnxRuntime\Microsoft.ML.OnnxRuntime.csproj -p:SelectedTargets=PreNet6 msbuild -t:build .\src\Microsoft.ML.OnnxRuntime\Microsoft.ML.OnnxRuntime.csproj -p:SelectedTargets=PreNet6

Need to run msbuild twice - once to restore which creates some json configs that are needed like Microsoft.ML.OnnxRuntime\obj\project.assets.json, and once to build using the configs.

Build net6 targets dotnet build .\src\Microsoft.ML.OnnxRuntime\Microsoft.ML.OnnxRuntime.csproj -p:SelectedTargets=Net6

The dotnet build does the restore internally.

Create project.assets.json in obj dir with all targets so the nuget package creation includes them all msbuild -t:restore .\src\Microsoft.ML.OnnxRuntime\Microsoft.ML.OnnxRuntime.csproj -p:SelectedTargets=All

Create nuget package msbuild .\OnnxRuntime.CSharp.proj -t:CreatePackage -p:OrtPackageId=Microsoft.ML.OnnxRuntime -p:Configuration=Debug -p:Platform="Any CPU"