Download Latest Version onnxruntime-win-x64-gpu_cuda13-1.28.2.zip (365.6 MB)
Email in envelope

Get an email when there's a new version of ONNX Runtime

Home / v1.28.2
Name Modified Size InfoDownloads / Week
Parent folder
onnxruntime-win-x64-gpu_cuda12-1.28.2.zip 2026-09-03 454.3 MB
onnxruntime-win-x64-gpu_cuda13-1.28.2.zip 2026-09-03 365.6 MB
onnxruntime-win-x64-1.28.2.zip 2026-09-03 78.6 MB
onnxruntime-win-arm64-1.28.2.zip 2026-09-03 79.7 MB
onnxruntime-win-arm64x-1.28.2.zip 2026-09-03 125.1 MB
onnxruntime-linux-aarch64-1.28.2.tgz 2026-09-03 8.1 MB
onnxruntime-linux-x64-1.28.2.tgz 2026-09-03 9.1 MB
onnxruntime-linux-x64-gpu_cuda12-1.28.2.tgz 2026-09-03 423.7 MB
onnxruntime-linux-x64-gpu_cuda13-1.28.2.tgz 2026-09-03 240.9 MB
onnxruntime-osx-arm64-1.28.2.tgz 2026-09-03 32.1 MB
ONNX Runtime v1.28.2 source code.tar.gz 2026-09-02 278.7 MB
ONNX Runtime v1.28.2 source code.zip 2026-09-02 285.6 MB
README.md 2026-09-02 768 Bytes
Totals: 13 Items   2.4 GB 4

This is a patch release on top of v1.28.1, containing a targeted fix for Compile API model serialization.

Highlights

Bug Fixes

  • Fixed Compile API callback serialization to prevent duplicate graph nodes, inputs, outputs, and value information in emitted optimized models, including models with embedded or external initializers (#32303)

Contributors

Thanks to our contributor for this release!

@adrastogi

Full Changelog: v1.28.1...v1.28.2

These release notes were drafted with assistance from GitHub Copilot.

Source: README.md, updated 2026-09-02