Add TorchAOHfQuantizer (#32306)

* Add TorchAOHfQuantizer

Summary:
Enable loading torchao quantized model in huggingface.

Test Plan:
local test

Reviewers:

Subscribers:

Tasks:

Tags:

* Fix a few issues

* style

* Added tests and addressed some comments about dtype conversion

* fix torch_dtype warning message

* fix tests

* style

* TorchAOConfig -> TorchAoConfig

* enable offload + fix memory with multi-gpu

* update torchao version requirement to 0.4.0

* better comments

* add torch.compile to torchao README, add perf number link

---------

Co-authored-by: Marc Sun <marc@huggingface.co>

docs/source/en/_toctree.yml

@@ -163,6 +163,8 @@
     title: FBGEMM_FP8
   - local: quantization/optimum
     title: Optimum
+  - local: quantization/torchao
+    title: TorchAO
   - local: quantization/contribute
     title: Contribute new quantization method
   title: Quantization Methods