`neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer`

Dequantize Cast Graph Rerewriter.

Module Contents

Classes

DequantizeCastOptimizer

Remove the Cast OP and set Dequantize output to B16 if the Cast OP output is BF16.

class neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer.DequantizeCastOptimizer(model)[source]: Remove the Cast OP and set Dequantize output to B16 if the Cast OP output is BF16.