com.microsoft - MatMulIntegerToFloat#

MatMulIntegerToFloat - 1#

Version

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

Summary

Inputs

Between 4 and 7 inputs.

  • A (heterogeneous) - T1:

  • B (heterogeneous) - T2:

  • a_scale (heterogeneous) - T3:

  • b_scale (heterogeneous) - T3:

  • a_zero_point (optional, heterogeneous) - T1:

  • b_zero_point (optional, heterogeneous) - T2:

  • bias (optional, heterogeneous) - T3:

Outputs

  • Y (heterogeneous) - T3:

Type Constraints

  • T1 in ( tensor(int8), tensor(uint8) ): Constrain input A data type to 8-bit integer tensor.

  • T2 in ( tensor(int8), tensor(uint8) ): Constrain input B data type to 8-bit integer tensor.

  • T3 in ( tensor(float) ): Constrain input a_scale, b_scale and output Y data type as float tensor.

Examples