`neural_compressor.torch.quantization.autotune`

Module Contents

`get_rtn_double_quant_config_set`(...)
`get_all_config_set`(...)
`autotune`(→ Optional[torch.nn.Module])	The main entry of auto-tune.

neural_compressor.torch.quantization.autotune.autotune(model: torch.nn.Module, tune_config: neural_compressor.common.base_tuning.TuningConfig, eval_fn: Callable, eval_args=None, run_fn=None, run_args=None, example_inputs=None) → torch.nn.Module | None[source]: The main entry of auto-tune.