com.microsoft - DynamicQuantizeMatMul

DynamicQuantizeMatMul - 1

Version

• name: DynamicQuantizeMatMul (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 3 and 5 inputs.

• A (heterogeneous) - T1:

• B (heterogeneous) - T2:

• b_scale (heterogeneous) - T1:

• b_zero_point (optional, heterogeneous) - T2:

• bias (optional, heterogeneous) - T1:

Outputs

• Y (heterogeneous) - T1:

Type Constraints

• T1 in ( tensor(float) ): Constrain input A, b_scale and output Y data type as float tensor.

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

Examples