[quant][graphmode][fix] Insert dequantize before use node (#34411)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/34411
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion
Test Plan:
python test/test_jit.py
Imported from OSS
Differential Revision: D20519603
fbshipit-source-id: 3e4c68d0a73142716e19ea6a64ae3a5d6d51fa41