Add INC WoQ and remove ITREX dependency

[changwangss]

What does this PR do?

I raise this PR based #841 . INC 3.0.2 released，we plan remove ITREX dependency and base INC to apply WOQ. @echarlaix

# quantize
from neural_compressor.transformers import GPTQConfig
from optimum.intel.neural_compressor import INCModelForCaudalLM
quantization_config = GPTQConfig(tokenizer=tokenizer_name, dataset=dataset_name)
model =  INCModelForCaudalLM.from_pretrained(model_name_or_path, quantization_config=quantization_config)
model.save_pretrained(“output_dir”)
# loading
model = INCModelForCaudalLM.from_pretrained(“output_dir”)

Fixes # (issue)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

[IlyasMoutawwakil]

Suggested change

	if optim_args.apply_quantization and optim_args.quantization_approach in {"weight_only"}:
	if optim_args.apply_quantization and optim_args.quantization_approach == "weight_only":

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[echarlaix]

could this be determined from the model itself (that the model was quantized through ITREX) ?

[changwangss]

This is not noticeable to users. Only the code inside optimal-intel changes from import ITREX to import INC. Unfortunately, the model does not have an attribute to indicate the source.

[echarlaix]

added a check here 08091bc : checking the quantization configuration (if present + matching algorithm parameter)