feat: int8 granite addon

[andrea-fasoli]

Description of the change

1. modified i8i8 add-ons to support Granite architecture in FMS, by registering the adapter steps and adapter for granite. Also unified registration process across models.
2. fixed bug in Linear module string representation printing when bias=False.

Was the PR tested

• I have ensured all unit tests pass

[chichun-charlie-liu]

is it required for AIU to make a "no bias" Linear layer into a Linear with bias (whose value is torch.zeros(1) )?

[andrea-fasoli]

It's required by the AIU in the sense that the custom op always expects a tensor as bias (not None nor a bool).

We could change W8A8Linear forward

fms-model-optimizer/fms_mo/aiu_addons/i8i8/i8i8_aiu_linear.py

Line 181 in 848b766

return self.aiu_op(

such that if self.bias does not exist we can create a zero tensor on the fly, cast it to the right device, and pass it to the op. I thought it'd be a more impactful overhead than just instantiating it once.

[chichun-charlie-liu]

just want to make sure it's a requirement from downstream stack. 8)