Int8DynamicActivationInt8WeightConfig¶
- class torchao.quantization.Int8DynamicActivationInt8WeightConfig(layout: Optional[Layout] = PlainLayout(), act_mapping_type: Optional[MappingType] = MappingType.SYMMETRIC, weight_only_decode: bool = False, set_inductor_config: bool = True)[source]¶
Configuration for applying int8 dynamic symmetric per-token activation and int8 per-channel weight quantization to linear layers
