Feng Liu d33cb73389 Expose inference type in the mlir quantizer ... This is to prepare the 16 bits activation quantization release. The data type specified by this flag is only applied on the activations. PiperOrigin-RevId: 311478782 Change-Id: I5f63f0508011cc0b1b47a0debb35c17d3284eae9		2020-05-13 23:55:06 -07:00
..
toco_python_api_wrapper.cc	Expose inference type in the mlir quantizer	2020-05-13 23:55:06 -07:00