Resubmit "Fix NaN error in dynamic quantization in qLinear, re-enable test_quantized_rnn"" (#37458)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/37458
Original commit changeset: 0204c360ef2c
ghstack-source-id: 103069356
Test Plan: buck test caffe2/test:quantization -- 'test_quantized_rnn \(quantization\.test_quantization\.PostTrainingDynamicQuantTest\)' --print-passing-details --run-disabled
Reviewed By: jamesr66a
Differential Revision: D21287904
fbshipit-source-id: a60deb8bdcf6af4258d1c1b199fa2a5a90318528
