FuseCustomConfig

class torch.ao.quantization.fx.custom_config.FuseCustomConfig [source]

Custom configuration for fuse_fx().

Example usage:

fuse_custom_config = FuseCustomConfig().set_preserved_attributes(["attr1", "attr2"])

classmethod from_dict(fuse_custom_config_dict) [source]

Create a ConvertCustomConfig from a dictionary with the following items:

“preserved_attributes”: a list of attributes that persist even if they are not used in forward

This function is primarily for backward compatibility and may be removed in the future.

Return type

FuseCustomConfig

set_preserved_attributes(attributes) [source]

Set the names of the attributes that will persist in the graph module even if they are not used in the model’s forward method.

Return type

FuseCustomConfig

to_dict() [source]

Convert this FuseCustomConfig to a dictionary with the items described in from_dict().

Return type

Dict[str, Any]