Download Latest Version ONNX Runtime WebGPU Plugin EP v0.2.1 source code.zip (292.6 MB)
Email in envelope

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

Home / v1.27.1
Name Modified Size InfoDownloads / Week
Parent folder
onnxruntime-win-x64-gpu_cuda13-1.27.1.zip 2026-07-11 333.5 MB
onnxruntime-linux-aarch64-1.27.1.tgz 2026-07-10 7.8 MB
onnxruntime-linux-x64-1.27.1.tgz 2026-07-10 8.8 MB
onnxruntime-linux-x64-gpu_cuda12-1.27.1.tgz 2026-07-10 244.8 MB
onnxruntime-osx-arm64-1.27.1.tgz 2026-07-10 32.0 MB
onnxruntime-win-arm64-1.27.1.zip 2026-07-10 78.6 MB
onnxruntime-win-arm64x-1.27.1.zip 2026-07-10 122.5 MB
onnxruntime-win-x64-1.27.1.zip 2026-07-10 77.2 MB
onnxruntime-win-x64-gpu_cuda12-1.27.1.zip 2026-07-10 325.9 MB
onnxruntime-linux-x64-gpu_cuda13-1.27.1.tgz 2026-07-10 216.1 MB
ONNX Runtime v1.27.1 source code.tar.gz 2026-07-09 285.8 MB
ONNX Runtime v1.27.1 source code.zip 2026-07-09 292.4 MB
README.md 2026-07-09 2.2 kB
Totals: 13 Items   2.0 GB 4

This is a patch release on top of v1.27.0, containing targeted bug fixes, a CUDA QMoE decode-path optimization, and CI/build infrastructure fixes.

Bug Fixes

  • [MLAS] Fixed an igemm regression in the KleidiAI path (#28571)
  • Fixed a QMoE CPU livelock by eliminating nested intra-op parallelism (#29081)
  • Fixed a regression in graph-capture session initialization that rejected an empty graph (#29457)
  • Fixed CustomOp forward compatibility by capping the version instead of rejecting it (#29574)

Performance

NVIDIA CUDA EP

  • Added a QMoE GEMV fast path for batch-1 decode (#29038)

CI & Build Infrastructure

  • Fixed an incorrect identity for azcopy (#29274)
  • Fixed a brew install applesimutils failure by trusting the wix/brew tap (#29450)
  • Upgraded to Xcode 26 (#29468)
  • Stopped echoing the command when setting a VSO variable in mac-cpu-packing-jobs.yml (#29575)
  • Fixed the web e2e (npm/vite) and Python DML CI pipelines (#29609)

Contributors

Thanks to our 8 contributors for this release!

@tianleiwu, @chilo-ms, @edgchen1, @adrastogi, @damdoo01-arm, @JonathanC-ARM, @martin-klacer-arm, @sanaa-hamel-microsoft

Full Changelog: v1.27.0...v1.27.1

Source: README.md, updated 2026-07-09