New feature of adding Intel® Extension for Transformers weight-only quantization into Lightning Fabric API

Nobody has claimed this yet.

### Description & Motivation

Hello,

We are the team working on the development of [Intel® Extension for Transformers](https://github.com/intel/intel-extension-for-transformers). We would like to discuss the `quantize` feature in relation to our projects.

Allow us to provide an introduction to both projects firstly:
- [Intel® Extension for Transformers](https://github.com/intel/intel-extension-for-transformers) (ITREX) is an innovative toolkit to accelerate Transformer-based models on Intel platforms, in particular effective on 4th Intel Xeon Scalable processor Sapphire Rapids (codenamed Sapphire Rapids).

We would like to integrate ITREX into the PyTorch Lightning Fabric API. This integration could involve INT8/INT4/FP4/NF4 weight-only quantization feature.

We would like to ask if there is an opportunity for us to make some contributions in this regard.

Thanks

### Pitch

Here is a simple use case:

```python
from lightning.fabric.plugins import ITREXPrecision

precision = ITREXPrecision(mode="int8") # mode: Literal["int8", "int4_fullrange", "int4_clip", "nf4", "fp4_e2m1"]
fabric = Fabric(plugins=precision)
model = MyModel()
model = fabric.setup(model)
```
For more details of ITREX 4-bit, please refer to the medium blog of [Intel-Optimized Llama.CPP](https://medium.com/@NeuralCompressor/llm-performance-of-intel-extension-for-transformers-f7d061556176)

### Alternatives

_No response_

### Additional context

_No response_

cc @borda

Start by reviewing the Lightning Fabric API and the linked Intel® Extension for Transformers project, then compare the proposed ITREXPrecision/Fabric setup with existing precision integrations. The issue names no files, tests, or acceptance criteria, so clarify the supported quantization modes, integration surface, and validation plan before implementation.

Written by the indexing model from the issue text.