[quant] Make PerChannel Observer work with float qparams (#42690)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/42690
Add implementation for new qscheme per_channel_affine_float_qparams in observer
Test Plan:
python test/test_quantization.py TestObserver.test_per_channel_observers
Imported from OSS
Reviewed By: vkuzo
Differential Revision: D23070633
fbshipit-source-id: 84d348b0ad91e9214770131a72f7adfd3970349c