<Untitled>

C++ API example demonstrating how one can use MatMul with compressed weights.

C++ API example demonstrating how one can use MatMul with compressed weights.

Concepts:

• Asymmetric quantization

  • Scales: dnnl::primitive_attr::set_scales()

  • Zero points: dnnl::primitive_attr::set_zero_points()

• Operation fusion

• Create primitive once, use multiple times

• Weights pre-packing: use dnnl::memory::format_tag::any