[quant] Removing unnecessary import from torch/quantization/quantize.py (#64910)

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/64910

This bled through from the original location. Removing it is not just refactoring, but also prevents potential recursive imports.
ghstack-source-id: 138112663

Test Plan: `buck test mode/dev //caffe2/test:quantization`

Reviewed By: vkuzo

Differential Revision: D30882924

fbshipit-source-id: 8652a334a5186c635761ea5e50f978d1f1078c12

diff --git a/torch/quantization/quantize.py b/torch/quantization/quantize.py
index 5b0f4ed..d9fcf1d 100644 (file)
--- a/torch/quantization/quantize.py
+++ b/torch/quantization/quantize.py
@@ -7,8 +7,6 @@ If you are adding a new entry/functionality, please, add it to the
 here.
 """
 
-import torch
-
 from torch.ao.quantization.quantize import _convert
 from torch.ao.quantization.quantize import _observer_forward_hook
 from torch.ao.quantization.quantize import _propagate_qconfig_helper