PNP: early FX numeric suite tool to quantize each layer N times (#80521)
Summary:
This PR is an early prototype of a tool to quantize each layer of a model
N times, with N qconfigs each. We follow the design agreed upon in
https://fburl.com/gdoc/e1gaq3ih .
Current API:
```
m = M().eval()
example_input = (torch.randn(2, 2),)
qconfig_mappings = [
QConfigMapping().set_global(torch.quantization.default_qconfig),
QConfigMapping().set_global(torch.quantization.default_dynamic_qconfig),
]
backend_config = get_native_backend_config()
msp = prepare_n_shadows_model(
m, example_input, qconfig_mappings, backend_config)
for _ in range(2):
msp(*example_input)
msq = convert_n_shadows_model(msp)
msq(*example_input)
results = extract_results_n_shadows_model(msq)
print_comparisons_n_shadows_model(results)
// example output
subgraph_idx ref_node_name best_idx 1 2
-------------- --------------- ---------- ------- -------
subgraph_0 fc1 2 42.0834 42.6279
subgraph_1 fc2 2 43.7259 50.0593
```
Test plan:
```
python test/test_quantization.py -k test_n_shadows
```
Differential Revision: [D37650332](https://our.internmc.facebook.com/intern/diff/D37650332)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/80521
Approved by: https://github.com/jerryzh168, https://github.com/andrewor14
