Class ov::op::internal::DynamicQuantize#

class DynamicQuantize : public ov::op::Op#

Operator performing Dynamic Quantize.

Public Functions

DynamicQuantize(const Output<Node> &data, std::vector<uint64_t> group_sizes, element::Type dt_scale)#

Constructs an DynamicQuantize operation.

Parameters:

  • data – Input tensor with data

  • group_sizes – Group sizes for dynamic quantization

  • dt_scale – Data type for scale output

virtual void validate_and_infer_types() override#

Verifies that attributes and inputs are consistent and computes output shapes and element types. Must be implemented by concrete child classes so that it can be run any number of times.

Throws if the node is invalid.