distill

Modules

`modelopt.torch.distill.config`	Configurations for distillation modes.
`modelopt.torch.distill.distillation`	API for converting a model into a modelopt.torch.distill.DistillationModel to be used directly in training.
`modelopt.torch.distill.distillation_model`	Meta-model wrapper to support knowledge-distillation learning.
`modelopt.torch.distill.loss_balancers`	Basic loss balancers for Distillation task.
`modelopt.torch.distill.losses`	Different types of distillation losses.
`modelopt.torch.distill.mode`	Module implementing and describing modes that can be used during the NAS convert process.
`modelopt.torch.distill.registry`	A dynamic module registry that holds information about available DynamicModules for Distillation-related purposes.

Distillation Task API subpackage for torch.