574a9e12bb
* Add compressed-tensors HFQuantizer implementation * flag serializable as False * run * revive lines deleted by ruff * fixes to load+save from sparseml, edit config to quantization_config, and load back * address satrat comment * compressed_tensors to compressed-tensors and revert back is_serializable * rename quant_method from sparseml to compressed-tensors * tests * edit tests * clean up tests * make style * cleanup * cleanup * add test skip for when compressed tensors is not installed * remove pydantic import + style * delay torch import in test * initial docs * update main init for compressed tensors config * make fix-copies * docstring * remove fill_docstring * Apply suggestions from code review Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com> * review comments * review comments * comments - suppress warnings on state dict load, tests, fixes * bug-fix - remove unnecessary call to apply quant lifecycle * run_compressed compatability * revert changes not needed for compression * no longer need unexpected keys fn * unexpected keys not needed either * Apply suggestions from code review Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com> * add to_diff_dict * update docs and expand testing * Update _toctree.yml with compressed-tensors * Update src/transformers/utils/quantization_config.py Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> * update doc * add note about saving a loaded model --------- Co-authored-by: George Ohashi <george@neuralmagic.com> Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com> Co-authored-by: Sara Adkins <sara@neuralmagic.com> Co-authored-by: Sara Adkins <sara.adkins65@gmail.com> Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> Co-authored-by: Dipika Sikka <ds3822@columbia.edu> Co-authored-by: Dipika <dipikasikka1@gmail.com>
1.8 KiB
Executable File
Quantization
Quantization techniques reduce memory and computational costs by representing weights and activations with lower-precision data types like 8-bit integers (int8). This enables loading larger models you normally wouldn't be able to fit into memory, and speeding up inference. Transformers supports the AWQ and GPTQ quantization algorithms and it supports 8-bit and 4-bit quantization with bitsandbytes.
Quantization techniques that aren't supported in Transformers can be added with the [HfQuantizer] class.
Learn how to quantize models in the Quantization guide.
QuantoConfig
autodoc QuantoConfig
AqlmConfig
autodoc AqlmConfig
AwqConfig
autodoc AwqConfig
EetqConfig
autodoc EetqConfig
GPTQConfig
autodoc GPTQConfig
BitsAndBytesConfig
autodoc BitsAndBytesConfig
HfQuantizer
autodoc quantizers.base.HfQuantizer
HqqConfig
autodoc HqqConfig
FbgemmFp8Config
autodoc FbgemmFp8Config
CompressedTensorsConfig
autodoc CompressedTensorsConfig
TorchAoConfig
autodoc TorchAoConfig