ORT 1.28.0 Release Candidates Available for Testing

[tianleiwu]

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
Release manager: @tianleiwu

Python Packages

CPU: onnxruntime
CUDA 13: onnxruntime-gpu
CUDA 12: onnxruntime-gpu

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
Microsoft.ML.OnnxRuntime.Managed

CUDA 13

Microsoft.ML.OnnxRuntime.Gpu
Microsoft.ML.OnnxRuntime.Gpu.Linux
Microsoft.ML.OnnxRuntime.Gpu.Windows
Microsoft.ML.OnnxRuntime.Managed

CUDA 12

Microsoft.ML.OnnxRuntime.Gpu
Microsoft.ML.OnnxRuntime.Gpu.Linux
Microsoft.ML.OnnxRuntime.Gpu.Windows
Microsoft.ML.OnnxRuntime.Managed