Intel OpenVINO runtime for Neural Network Engine (NNE).

Accelerates AI inference on Intel CPU, GPU, and NPU devices.

Features Include:

- Model Support: ONNX and OpenVINO IR models

- NPU Inference: Offload existing inference tasks to an NPU device

- OS Support: Seamlessly runs on Windows or Linux

- Performance: Models are compiled and optimized on-demand for Intel devices