quark.torch.pruning.config

Contents

`quark.torch.pruning.config`#

Module Contents#

Classes#

class quark.torch.pruning.config.Config#

A class that encapsulates comprehensive pruning configurations for a machine learning model, allowing for detailed and hierarchical control over pruning parameters across different model components.

Parameters:

algo_config (Optional[AlgoConfig]) – Optional configuration for the pruning algorithm, such as OSSCAR. After this process, the params will be reduced. Default is None.
log_severity_level (Optional[int]) – 0:DEBUG, 1:INFO, 2:WARNING. 3:ERROR, 4:CRITICAL/FATAL. Default is 1.