com.microsoft - QLinearAdd#

QLinearAdd - 1#

Version

  • name: QLinearAdd (GitHub)

  • domain: com.microsoft

  • since_version: 1

  • function:

  • support_level: SupportType.COMMON

  • shape inference: True

This version of the operator has been available since version 1 of domain com.microsoft.

Summary

Inputs

Between 7 and 8 inputs.

  • A (heterogeneous) - T:

  • A_scale (heterogeneous) - tensor(float):

  • A_zero_point (optional, heterogeneous) - T:

  • B (heterogeneous) - T:

  • B_scale (heterogeneous) - tensor(float):

  • B_zero_point (optional, heterogeneous) - T:

  • C_scale (heterogeneous) - tensor(float):

  • C_zero_point (optional, heterogeneous) - T:

Outputs

  • C (heterogeneous) - T:

Type Constraints

  • T in ( tensor(int8), tensor(uint8) ): Constrain input and output types to 8 bit signed and unsigned tensors.

Examples