QLinearMatMul (CPU)
===================

* Domain: ``ai.onnx``
* Device: ``CPU``
* Kernel: ``onnx_light_cpu::QLinearMatMul``
* Supported types: ``INT8``, ``UINT8``
* Opset bounds: none

Operator support
----------------

The standard ONNX schema and any standard shape inference come from onnx-light. No additional shape, peak-memory, fusion-pattern, or gradient implementation is registered by onnx-light-cpu for this operator.