1.24.2 release candidate available for testing

[tianleiwu]

ORT 1.24.2 will be released next week. RC1 builds are available now for testing. If you encounter issues, please report them by responding in this issue.

Release branch: rel-1.24.2
Release manager: @tianleiwu

What's new?

• Windows Arm64 in python cpu package.

Bug fixes:

• Nuget DLL loading in Linux and Mac OS (Related issue: 1.24.1 nuget package is broken on linux #27263)
• Add Mac OS support to Java package. (Related issue: ORT 1.24 release candidate available for testing #27130 (comment))
  A few other fixes for WebGPU and QNN, see ORT 1.24.2 release cherry pick round 1 #27330 for all commits.

Python Packages

CPU: https://aiinfra.visualstudio.com/PublicPackages/_artifacts/feed/ORT-Nightly/PyPI/onnxruntime/overview/1.24.2.dev20260213008
CUDA 12: https://aiinfra.visualstudio.com/PublicPackages/_artifacts/feed/ORT-Nightly/PyPI/onnxruntime-gpu/overview/1.24.2.dev20260212002
CUDA 13: https://aiinfra.visualstudio.com/PublicPackages/_artifacts/feed/ort-cuda-13-nightly/PyPI/onnxruntime-gpu/overview/1.24.2.dev20260212003

Installation

First, you might need uninstall existed onnx runtime packages, and install required packages like

pip uninstall onnxruntime onnxruntime-gpu -y
pip install flatbuffers numpy packaging protobuf sympy

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

CPU

pip install --pre --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/ORT-Nightly/pypi/simple/ onnxruntime-gpu==1.24.2.dev20260213008

CUDA 12.x

pip install --pre --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/ORT-Nightly/pypi/simple/ onnxruntime-gpu==1.24.2.dev20260212002

CUDA 13.x

pip install --pre --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/ort-cuda-13-nightly/pypi/simple/ onnxruntime-gpu==1.24.2.dev20260212003

Nuget packages

The version is 1.24.2-rc.1 for all nuget packages below.

CPU

Microsoft.ML.OnnxRuntime
Microsoft.ML.OnnxRuntime.Gpu.Managed

CUDA 12

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

CUDA 13

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

QNN

Microsoft.ML.OnnxRuntime.QNN

Java packages

https://repo1.maven.org/maven2/com/microsoft/onnxruntime/onnxruntime/1.24.2-rc1/
https://repo1.maven.org/maven2/com/microsoft/onnxruntime/onnxruntime_gpu/1.24.2-rc1
https://repo1.maven.org/maven2/com/microsoft/onnxruntime/onnxruntime-android/1.24.2-rc.1
https://repo1.maven.org/maven2/com/microsoft/onnxruntime/onnxruntime-android-qnn/1.24.2-rc.1

[ladeak]

Microsoft.ML.OnnxRuntime seems to be missing all native dependencies now.

[theolivenbaum]

@tianleiwu any updates on the underlying issue of low quality code being merged from copilot as seen in #27263 ?
Is there a review planned for all AI-generated commits to make sure there's no more minefields laying dormant on this release?