[quant][graphmode] weight/bias of linear/conv can be reused for multiple ops (#35221)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/35221
When weight is reused, we only need to insert one observer for the weight
Test Plan:
python test/test_jit.py
Imported from OSS
Differential Revision: D20602492
fbshipit-source-id: e003e6316f6615f3526f0d00fb7b722148b4749b