LayerQuantizationSettings
CLASS - LayerQuantizationSettings(
- weights_num_bits:
int
= 8- activations_num_bits:
int
= 8- skip_tail_quantization:
Optional[bool]
= None- automatic_skip_quantization:
bool
= True- quantization_sensitivity_threshold:
Union[int, float, None]
= None- skip_quantization:
bool
= False- skip_quantization_downstream:
bool
= False- skip_quantization_until:
Union[str, Tuple[str], List[str], None]
= None)
Ancestors - (BaseQATQuantizationSettings
, BaseQuantizationSettings
)
Quantization Settings for a specific Layer that can be set in Settings.
Class Variables
- skip_quantization (
bool
) - Whether or not to Skip Quantization for a specific Layer. - skip_quantization_downstream (
bool
) - Whether or not to Skip Quantization for the current Layer and everything below it in the Graph. - skip_quantization_until (
Union[str, Tuple[str], List[str], None]
) - Skip Quantization from the layer name the LayerQuantizationSettings is assigned to until another layer name