Remove fbgemm_is_cpu_supported in favor of torch.backends.quantized.supported_qengines (#26840)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/26840
Cleaning up top-level namespace. Also cosmetic changes to torch.backends.quantized
Test Plan: Imported from OSS
Differential Revision: D17604403
Pulled By: dzhulgakov
fbshipit-source-id: c55af277ea7319d962a82a6120f65ccd47a60abc
