Optimum

You are viewing v1.2.1 version. A newer version v1.23.3 is available.

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

Optimization

IncOptimizer

class optimum.intel.IncOptimizer

< source >

( model: typing.Union[transformers.modeling_utils.PreTrainedModel, torch.nn.modules.module.Module] quantizer: typing.Optional[neural_compressor.experimental.quantization.Quantization] = None pruner: typing.Optional[neural_compressor.experimental.pruning.Pruning] = None )

←Configuration Quantization→