MatMul - version 9#

This page documents version 9 of operator MatMul. See MatMul for the latest version (since version 13).

  • Domain: ai.onnx

  • Since version: 9

Matrix product that behaves like numpy.matmul.

Inputs

  • A (T): N-dimensional matrix A

  • B (T): N-dimensional matrix B

Outputs

  • Y (T): Matrix multiply results from A * B

Type Constraints

  • T: Constrain input and output types to float/int tensors. Allowed types: tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64).

Differences with previous version (1)#

SchemaDiff: MatMul (domain 'ai.onnx')

  • old version: 1

  • new version: 9

  • breaking: no

Type constraints:

  • changed ‘T’: added types: [‘tensor(int32)’, ‘tensor(int64)’, ‘tensor(uint32)’, ‘tensor(uint64)’]