ONNX Runtime ships its first separately packaged CUDA provider
Microsoft released ONNX Runtime CUDA Plugin EP 0.1.0 as a separate wheel and NuGet package and made the plugin core the default CUDA provider implementation. It includes CUDA Graph capture and replay, user streams, profiling and memory statistics, quantized MoE and FP4 paths, optional cuDNN and cuFFT, and Windows ARM64 packages.
Why it matters: CUDA inference can now be packaged and upgraded with a narrower provider boundary, but the new default implementation and 0.1.0 maturity make compatibility and rollback evidence essential.