neural_compressor.adaptor.ox_utils.operators.attention

Attention operator.

Module Contents

Classes

AttentionOperator

Attention operator.

QAttentionOperator

QAttention operator.

class neural_compressor.adaptor.ox_utils.operators.attention.AttentionOperator(onnx_quantizer, onnx_node)[source]

Attention operator.

class neural_compressor.adaptor.ox_utils.operators.attention.QAttentionOperator(onnx_node, children, initializers)[source]

QAttention operator.