per channel quantization support (#25134)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/25134
copy of https://our.intern.facebook.com/intern/diff/D16909378/
it was reverted in https://our.intern.facebook.com/intern/diff/D16997422/
Per channel quantization support in qconv2d + tests
ghstack-source-id: 88992610
Test Plan:
buck test mode/dev caffe2/test:quantized -- --print-passing-details
```
Finished test run: https://our.intern.facebook.com/intern/testinfra/testrun/4222124656103386
Summary (total time 64.42s):
PASS: 33
FAIL: 0
SKIP: 3
caffe2/test:quantized - test_qlinear (test_quantized.TestDynamicQuantizedLinear)
caffe2/test:quantized - test_qnnpack_relu (test_quantized.TestQNNPackOps)
caffe2/test:quantized - test_qnnpack_linear (test_quantized.TestQNNPackOps)
FATAL: 0
TIMEOUT: 0
OMIT: 0
```
Differential Revision: D16999104
fbshipit-source-id: 008447ffbc0144f0fc76f3cf143a2f69b65922fd
