ONNX has AVX512 CPU kernels too, and openvino uses ONNX internally (and ONNX supports openvino backend)

> openvino uses ONNX internally

OpenVINO only uses ONNX to parse the model, not to execute it. It runs computations through its own highly optimized inference engine specifically designed for Intel hardware. It doesn't rely on the ONNX engine at all, and it will even automatically convert eligible model weights to BF16 for you