feat: Add int8 sd conversion function for aiu

[andrea-fasoli]

Description of the change

This PR introduces a conversion function for the state dictionary of an INT8-quantized model created with fms-mo.
By calling save_sd_for_aiu, a new state dictionary which complies with AIU requirements is generated and saved.
This new state dictionary / checkpoint can be loaded using fms get_model function in combination with the INT8 add-ons already present in fms-mo (see fms_mo/aiu_addons/).

The following processing steps are taken by this conversion function:

• a new smoothquant scale is created by combining smoothquant weight and activation scales (and smoothquant alpha)
• weights are first scaled, then converted to signed integer format (torch.int8)
• zero_shift is computed and added to the state dictionary, if needed
• keys/values not needed on the AIU are purged from the dictionary

Was the PR tested

• I have ensured all unit tests pass

[andrea-fasoli]

by adding SAWB recomputation in the presence of narrow INT weights distributions, this PR also addresses issue #109

[andrea-fasoli]

needs testing and unit testing...

[andrea-fasoli]

The PR has been tested with multiple INT8 quantization configurations and is ready to be merged.

Unit tests are missing, will be added at a later date (cc: @BrandonGroth)

Conversion of a checkpoint trained with smoothquant is not supported when combined with SAWB-based weights recomputation. This feature will be implemented as part of issue #112. The feature is not strictly needed for INT8 RoBERTa, where smoothquant-free quantization configurations perform well. It may be needed for INT8 LLMs enablement.