test_op_qnn_requantize.py
12.6 KB
-
[QNN] Optimize lowering for requantize and FixedPointMultiply. (#4798) · 23f3988b
* [QNN] Optimize lowering for requantize and FixedPointMultiply. * Add check for requantize scale gt 1. * Added test case.
Animesh Jain committed