[Onnxifi] Support quantized output in Onnxifi (#39230)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/39230
Pull Request resolved: https://github.com/pytorch/glow/pull/4555
With this we now support cutting in the middle of the quantized domain for Onnxifi. This will allow us to observe intermediate quantized value during Onnxifi. Input still has to be non-quantized tensor though. This will be a follow-up.
Test Plan:
```
buck test glow/fb/test/numerics:test_fc_nnpi_int8nnpi -- test_quantize
```
Reviewed By: hyuen
Differential Revision: D21783368
fbshipit-source-id: 51001246e9e0357d7ba90bf12279b644f5f30221
