Enable AWQ on Intel GPU.

[xiaowangintel]

Following pytorch/pytorch#153019 requests, we enable awq-uint4 for Intel GPU in pytorch/ao after RTN ready. Currently, the implementation of awq-uint4 uses the ZeroPointDomain.FLOAT and ZeroPointDomain.INT.

How to run awq quantization model:

cd torchao/prototype/awq

#for zero point int domain:
python example.py --device xpu --zero_point_domin=int  huggingface-model(such as meta-llama/Llama-3.1-8B-Instruct) awq-uint4-128

#for zero point float domain:
python example.py --device xpu huggingface-model(such as meta-llama/Llama-3.1-8B-Instruct) awq-uint4-128

#Results of meta-llama/Llama-3.1-8B-Instruct for int domain on Intel GPU:
{'perplexity': {'perplexity': 10.099576950073242, 'prediction_time': 0.20489671968780787}}

#Results of meta-llama/Llama-3.1-8B-Instruct for float domain on Intel GPU:
{'perplexity': {'perplexity': 10.166366577148438, 'prediction_time': 0.12182355982012454}}

#Results of meta-llama/Llama-3.1-8B-Instruct for float domain on NVIDIA-A100 GPU:
Results: {'perplexity': {'perplexity': 10.160041809082031, 'prediction_time': 0.4466673863672577}}

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2248

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[xiaowangintel]

@liangan1 Can you help to review this PR?

[liangan1]

how about perplexity on cuda?

[liangan1]

LGTM

[liangan1]

@EikanWang