More fixes needed when QuantizationConfig is None

[rahul-tuli]

Description taken from #180

CompressedTensorsHfQuantizerattempts to useapply_quantization_config` to apply the quantization config to the model

def _process_model_before_weight_loading(self, model, **kwargs):
        from compressed_tensors.quantization import apply_quantization_config

        ct_quantization_config = self.compressor.quantization_config
        apply_quantization_config(model, ct_quantization_config, run_compressed=True)

However, self.compressor.quantization_config can be None in the case that only sparsity is present. This does not align with the function contract of apply_quantization_config. In such a case, an error is thrown.

def apply_quantization_config(
    model: Module, config: QuantizationConfig, run_compressed: bool = False
) -> Dict:

This PR builds on top of #180 and adds more bugfixes needed for the case when a None quantization config is passed in by the HfQuantizer

[dsikka]

Not required. See pathway used by HFQuantizer:
https://github.com/huggingface/transformers/blob/55be7c4c483a01a7e03e55a8756fc4385ec08ffc/src/transformers/quantizers/quantizer_compressed_tensors.py#L40

[kylesayrs]

#173

[dsikka]

Do we use this function outside of apply_quantization_config? If not, we would never hit the None case?

[kylesayrs]

Seems like the only use of process_quantization_config is by apply_quantization_config.
What is the purpose of this change?

[rahul-tuli]

This was relevant to the reloading a compressed model case, as per discussion offline, this is not needed