BackendPatternConfig

class torch.ao.quantization.backend_config.BackendPatternConfig(pattern)

Config for ops defined in BackendConfig. For a detailed example usage, see BackendConfig.

add_dtype_config(dtype_config)

Add a set of supported input/output activation, weight, and bias data types for this pattern.

Return type:

BackendPatternConfig

classmethod from_dict(backend_pattern_config_dict)

Create a BackendPatternConfig from a dictionary with the following items:

“pattern”: the pattern being configured “observation_type”: the ObservationType that specifies how observers should be inserted for this pattern “dtype_configs”: a list of dictionaries that represents DTypeConfig s “root_module”: a torch.nn.Module that represents the root for this pattern “qat_module”: a torch.nn.Module that represents the QAT implementation for this pattern “reference_quantized_module”: a torch.nn.Module that represents the reference quantized implementation for this pattern’s root module. “fused_module”: a torch.nn.Module that represents the fused implementation for this pattern “fuser_method”: a function that specifies how to fuse the pattern for this pattern

Return type:

BackendPatternConfig

set_dtype_configs(dtype_configs)

Set the supported input/output activation, weight, and bias data types for this pattern, overriding all previously registered data types.

Return type:

BackendPatternConfig

set_fused_module(fused_module)

Set the module that represents the fused implementation for this pattern.

Return type:

BackendPatternConfig

set_fuser_method(fuser_method)

Set the function that specifies how to fuse the pattern for this pattern.

Return type:

BackendPatternConfig

set_observation_type(observation_type)

Set how observers should be inserted for this pattern. See ObservationType for details

Return type:

BackendPatternConfig

set_qat_module(qat_module)

Set the module that represents the QAT implementation for this pattern.

Return type:

BackendPatternConfig

set_reference_quantized_module(reference_quantized_module)

Set the module that represents the reference quantized implementation for this pattern’s root module.

Return type:

BackendPatternConfig

set_root_module(root_module)

Set the module that represents the root for this pattern. For example, the root module for torch.nn.intrinsic.LinearReLU should be torch.nn.Linear.

Return type:

BackendPatternConfig

to_dict()

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

Return type:

Dict[str, Any]