ORT 1.28.0 Release Candidates Available for Testing

Nobody has claimed this yet.

ORT 1.28.0 will be released soon, pending successful validation. Release candidate builds are available now for testing. If you encounter issues, please report them by responding in this issue.

Release branch: [rel-1.28.0](https://github.com/microsoft/onnxruntime/tree/rel-1.28.0)
Release manager: @tianleiwu

## Python Packages
CPU: [onnxruntime](https://aiinfra.visualstudio.com/PublicPackages/_artifacts/feed/ORT-Nightly/PyPI/onnxruntime/overview/1.28.0.dev20260722005)
CUDA 13: [onnxruntime-gpu](https://aiinfra.visualstudio.com/PublicPackages/_artifacts/feed/ORT-Nightly/PyPI/onnxruntime-gpu/overview/1.28.0.dev20260722004)
CUDA 12: [onnxruntime-gpu](https://aiinfra.visualstudio.com/PublicPackages/_artifacts/feed/onnxruntime-cuda-12/PyPI/onnxruntime-gpu/overview/1.28.0.dev20260722004)

### Installation Python Packages

First, you might need uninstall existed packages like
```
pip uninstall onnxruntime onnxruntime-gpu -y
```

Then choose only one of the following based on cuda version (or CPU only) to install:

#### CUDA 13.x
```
pip install flatbuffers numpy packaging protobuf
pip install --pre --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/ORT-Nightly/pypi/simple/ onnxruntime-gpu==1.28.0.dev20260722004
```

#### CUDA 12.x
```
pip install flatbuffers numpy packaging protobuf sympy coloredlogs
pip install --pre --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple/ onnxruntime-gpu==1.28.0.dev20260722004
```

#### CPU Only
```
pip install flatbuffers numpy packaging protobuf sympy coloredlogs
pip install --pre --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/ORT-Nightly/pypi/simple/ onnxruntime==1.28.0.dev20260722005
```

## Nuget packages

### CPU:
[Microsoft.ML.OnnxRuntime](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime/1.28.0-rc.1)
[Microsoft.ML.OnnxRuntime.Managed](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.Managed/1.28.0-rc.1)

### CUDA 13
[Microsoft.ML.OnnxRuntime.Gpu](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.Gpu/1.28.0-rc.1)
[Microsoft.ML.OnnxRuntime.Gpu.Linux](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.Gpu.Linux/1.28.0-rc.1)
[Microsoft.ML.OnnxRuntime.Gpu.Windows](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.Gpu.Windows/1.28.0-rc.1)
[Microsoft.ML.OnnxRuntime.Managed](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.Managed/1.28.0-rc.1)

### CUDA 12
[Microsoft.ML.OnnxRuntime.Gpu](https://aiinfra.visualstudio.com/PublicPackages/_artifacts/feed/onnxruntime-cuda-12/NuGet/Microsoft.ML.OnnxRuntime.Gpu/overview/1.28.0-dev-20260722-1407-0368187f84)
[Microsoft.ML.OnnxRuntime.Gpu.Linux](https://aiinfra.visualstudio.com/PublicPackages/_artifacts/feed/onnxruntime-cuda-12/NuGet/Microsoft.ML.OnnxRuntime.Gpu.Linux/overview/1.28.0-dev-20260722-1407-0368187f84)
[Microsoft.ML.OnnxRuntime.Gpu.Windows](https://aiinfra.visualstudio.com/PublicPackages/_artifacts/feed/onnxruntime-cuda-12/NuGet/Microsoft.ML.OnnxRuntime.Gpu.Windows/overview/1.28.0-dev-20260722-1407-0368187f84)
[Microsoft.ML.OnnxRuntime.Managed](https://aiinfra.visualstudio.com/PublicPackages/_artifacts/feed/onnxruntime-cuda-12/NuGet/Microsoft.ML.OnnxRuntime.Managed/overview/1.28.0-dev-20260722-1407-0368187f84)

Start with the rel-1.28.0 release branch and the installation commands for the CPU or CUDA Python packages. Test the listed 1.28.0 release candidates in the relevant environment, including the NuGet packages if applicable. Done means reporting any encountered issues by responding in this issue; no source file or test entry point is named.

Written by the indexing model from the issue text.