[quant] Add reduce_range argument for qlinear_dynamic (#39041)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/39041
reduce_range option restricts the activation tensor to 7 bits instead of 8.
This is necessary to enable per channel quant for RNNs and LSTMs
Test Plan:
python test/test_quantization.py TestDynamicQuantizedLinear
Imported from OSS
Reviewed By: akinh
Differential Revision: D21769691
fbshipit-source-id: ef0e9873367f3c1b34091b0b3af788233ef60c6c