Fix the padding issue of quantized average pool operator (#28260)
Summary:
This is actually a bug in both testing and the average pool implementation.
In testing, we used the quantized value as float input and failed to padding the value with zero_point.
In op implementation, the size for averaging is not correct for padding case when count_include_pad is true.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/28260
Differential Revision: D18039960
Pulled By: lly-zero-one
fbshipit-source-id: 7b5d34498b60f5d574a276a22798c9f576944734
