Quantize FBS model with 16bit FX Quantization

Summary:
Pull Request resolved: https://github.com/facebookresearch/d2go/pull/531

As title, enable mixed precision FX quantization for FBS model.

This diff includes
1. Add `custom_prepare_fx` to the FBS d2go model to enable the FX quantization.
2. Add two new d2go config params `QUANTIZATION.ACT_BITS/QUANTIZATION.WEIGHTS`
3. Add `backend_config/qconfig_mapping` to d2go convert function calls.
4. Add an example FBS fx QAT config.

Reviewed By: ayushidalmia

Differential Revision: D45252545

fbshipit-source-id: 813b192fcdd66c17629490b8908ce8cd8534506a

d2go/quantization/fx.py

@@ -21,5 +21,5 @@ def get_prepare_fx_fn(cfg, is_qat):
 
 
 @fb_overwritable()
-def get_convert_fx_fn(cfg, example_inputs):
+def get_convert_fx_fn(cfg, example_inputs, qconfig_mapping=None, backend_config=None):
     return convert_fx

d2go/quantization/modeling.py

@@ -141,6 +141,8 @@ def add_quantization_default_configs(_C):
     _C.QUANTIZATION.MODULES = []
     # Lightning quantization callback name
     _C.QUANTIZATION.NAME = ""
+    _C.QUANTIZATION.ACT_BITS = 8
+    _C.QUANTIZATION.WEIGHT_BITS = 8
 
     # quantization-aware training
     _C.QUANTIZATION.QAT = CfgNode()