Intel OpenVINO is also quite punchy for CPU inference.
ONNX really is the universal format. If you can get your model exported to ONNX, running it on various platforms becomes much easier.*
*as long as every hardware platform supports the ops you use in your network and you're not doing anything too fancy/custom :P
Edit: often if you go through the ONNX intermediate format, be prepared to perform some 'network surgery' to clean up some conversion cruft, but also to remove training-only stuff left in the network...