ONNX Runtime v1.32.0
ONNX Runtime 1.32.0 adds CPU/GPU hybrid MoE offloading, shared-layout CPU QMoE kernels, and faster session initialization on large graphs.
The Deploy Log | Products | Free, no signup
3 versions of ONNX Runtime from Microsoft in The Deploy Log. From to . On the median a new version every 21 days, publisher's dates only; the longest wait was 27 days. The newest is v1.32.0. 2 versions in the last 30 days. Each links the publisher's own page.
| Version | Publisher's date | Days after the one before |
|---|---|---|
| v1.32.0 | 15 | |
| v1.30.1 | 27 | |
| v1.28.3 |
ONNX Runtime 1.32.0 adds CPU/GPU hybrid MoE offloading, shared-layout CPU QMoE kernels, and faster session initialization on large graphs.
Patch release with model-validation, memory-safety, Plugin EP data transfer, and build fixes.
Patch release with memory-safety, model-validation, plugin execution, and packaging fixes.
One line every time AI actually ships, around the clock, free on Threads and Bluesky. Every one is in The Deploy Log with its source.