deployedbyai
Follow

The Deploy Log | Products | Free, no signup

ONNX Runtime CUDA Plugin EP changelog

3 versions of ONNX Runtime CUDA Plugin EP from Microsoft in The Deploy Log. From to . On the median a new version every 18.5 days, publisher's dates only; the longest wait was 36 days. The newest is 0.4.0. 1 version in the last 30 days. Each links the publisher's own page.

Every version, newest first
VersionPublisher's dateDays after the one before
0.4.036
0.3.01
0.2.0

ONNX Runtime CUDA Plugin EP 0.4.0

CPU/GPU hybrid expert offloading, native GGUF/block-packed weight execution, Tensor-Core INT2/INT3/INT4 and offline K-packed NVFP4 QMoE kernels, long-context and speculative-decoding acceleration.

Microsoft | Tools and products | Published

SOURCE Microsoft, ONNX Runtime CUDA Plugin EP 0.4.0

ONNX Runtime CUDA Plugin EP 0.3.0

ONNX Runtime CUDA Plugin EP 0.3.0 adds sparse attention, packed continuous-batching, INT2 and mixed-width QMoE execution, and decode-kernel tuning.

Microsoft | Tools and products | Published

SOURCE Microsoft, ONNX Runtime CUDA Plugin EP 0.3.0

ONNX Runtime CUDA Plugin EP 0.2.0

Expanded quantized inference and attention support, kernel performance improvements, and reliability fixes.

Microsoft | Tools and products | Published

SOURCE Microsoft, ONNX Runtime CUDA Plugin EP 0.2.0

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.

The Saturday edition is the week in one, free to read on the site, and by email if you want it: get it by email.