move six worfklows to prototype

Summary:

Moves the following workflows to prototype:
* Int8DynamicActivationInt4WeightConfig
* Int4DynamicActivationInt4WeightConfig
* GemliteUIntXWeightOnlyConfig
* Float8StaticActivationFloat8WeightConfig
* UIntXWeightOnlyConfig
* FPXWeightOnlyConfig

Specifically:
1. move the deprecated workflows to
   `torchao/prototype/quantization/quant_api.py`
2. move utils to `torchao/quantization/utils.py` as needed
3. make some imports happen at runtime to avoid circular imports
4. change the warnings in the six workflows to reflect their new state

For now, keep BC by importing them from the old location. So, we get the
benefits of the simpler `quant_api.py` file with this PR, and we will defer breaking
BC until a future time to amortize the eng cost.

Test Plan:

CI

Reviewers:

Subscribers:

Tasks:

Tags:
ghstack-source-id: 6e22be1
ghstack-comment-id: 3657392357
Pull-Request: #3491

Author: vkuzo