:orphan:

:py:mod:`neural_compressor.adaptor.torch_utils.gptq`
====================================================

.. py:module:: neural_compressor.adaptor.torch_utils.gptq


Module Contents
---------------

Classes
~~~~~~~

.. autoapisummary::

   neural_compressor.adaptor.torch_utils.gptq.GPTQuantizer
   neural_compressor.adaptor.torch_utils.gptq.GPTQ



Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.adaptor.torch_utils.gptq.is_leaf
   neural_compressor.adaptor.torch_utils.gptq.trace_gptq_target_blocks
   neural_compressor.adaptor.torch_utils.gptq.find_layers
   neural_compressor.adaptor.torch_utils.gptq.find_layers_name
   neural_compressor.adaptor.torch_utils.gptq.log_quantizable_layers_per_transformer
   neural_compressor.adaptor.torch_utils.gptq.quantize



.. py:function:: is_leaf(module)

   Judge whether a module has no child-modules.

   :param module: torch.nn.Module

   :returns: whether a module has no child-modules.
   :rtype: a bool


.. py:function:: trace_gptq_target_blocks(module, module_types=[torch.nn.ModuleList, torch.nn.Sequential])

   Search transformer stacked structures, which is critical in LLMs and GPTQ execution.

   :param module: torch.nn.Module
   :param module_types: List of torch.nn.Module.

   :returns:

             gptq_related_blocks = {
                 "embeddings": {}, # Dict embedding layers before transformer stack module,
                 "transformers_pre": {}, # TODO
                 "transformers_name": string. LLMs' transformer stack module name ,
                 "transformers": torch.nn.ModuleList. LLMs' transformer stack module,
                 "transformers": {}, Dict# TODO
             }


.. py:function:: find_layers(module, layers=[nn.Conv2d, nn.Conv1d, nn.Linear, transformers.Conv1D], name='')

   Get all layers with target types.


.. py:function:: find_layers_name(module, layers=[nn.Conv2d, nn.Conv1d, nn.Linear, transformers.Conv1D], name='')

   Get all layers with target types.


.. py:function:: log_quantizable_layers_per_transformer(transformer_blocks, layers=[nn.Conv2d, nn.Conv1d, nn.Linear, transformers.Conv1D])

   Print all layers which will be quantized in GPTQ algorithm.


.. py:function:: quantize(x, scale, zero, maxq)

   Do quantization.


.. py:class:: GPTQuantizer(model, weight_config={}, dataloader=None, nsamples=128, use_max_length=True, pad_max_length=2048, device=None, layer_wise=False)




   Main API for GPTQ algorithm.

   Please refer to:
   GPTQ: Accurate Post-training Compression for Generative Pretrained Transformers
   url: https://arxiv.org/abs/2210.17323


.. py:class:: GPTQ(layer, W, device='cpu')


   Please refer to:
   GPTQ: Accurate Post-training Compression for Generative Pretrained Transformers (https://arxiv.org/abs/2210.17323)