Move QAT out of prototype

Summary: Move QAT out of prototype so we can provide stronger
BC guarantees moving forward.

**(Future) BC-breaking notes**

Note: This commit itself doesn't break BC yet. A future PR
will do that. The following is just to save this BC breaking
note somewhere.

Before:
```
from torchao.quantization.prototype.qat import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.prototype.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.prototype.qat.fake_quantizer import (
    FakeQuantizer,
)
```

After:
```
from torchao.quantization.qat import (
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
)
from torchao.quantization.qat.linear import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.qat.fake_quantizer import (
    FakeQuantizer,
)
```

Test Plan:
python test/quantization/test_qat.py

ghstack-source-id: add9dca
Pull Request resolved: #1091

* UI and API implementation for base64 encoded image input

* Fix multimodal input when no image prompt is present

* Address comments

---------

Co-authored-by: vmpuri <puri@meta.com>