Skip to content
Commit 54f4522a authored by Jing Pu's avatar Jing Pu Committed by A. Unique TensorFlower
Browse files

Specalize f32->i8/u8 Quanitization with C++ native arithmetic to optimize performance. 

The CL adds a rounding mode flag to the class and changes the default to rmNearestTiesToAway from rmNearestTiesToEven because 1) Tensorflow QuantizeV2 ops uses rmNearestTiesToAway; 2) the specialization only implements rmNearestTiesToAway.

PiperOrigin-RevId: 270600739
parent 541f1945
Show whitespace changes
Inline Side-by-side
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please to comment