Support AutoRound quantization method for intel GPU

[PenghuiCheng]

Type of Change

support auto-round quantization for intel GPU
No API changed

Description

support auto-round quantization for intel GPU

Expected Behavior & Potential Risk

Quantized model with the auto-round method.

How has this PR been tested?

Local tested

[github-actions]

⚡ Required checks status: All passing 🟢

Groups summary

🟢 Format Scan Tests workflow

Check ID	Status	Error details
format-scan (pylint)	success		✅
format-scan (bandit)	success		✅
format-scan (cloc)	success		✅
format-scan (cpplint)	success		✅

These checks are required after the changes to intel_extension_for_transformers/transformers/llm/evaluation/lm_eval/evaluator.py, intel_extension_for_transformers/transformers/llm/quantization/nn/modules.py, intel_extension_for_transformers/transformers/llm/quantization/utils.py, intel_extension_for_transformers/transformers/modeling/modeling_auto.py, intel_extension_for_transformers/transformers/utils/config.py.

🟢 Optimize Unit Test workflow

Check ID	Status	Error details
optimize-unit-test-baseline	success		✅
optimize-unit-test-PR-test	success		✅
Genreate-OptimizeUT-Report	success		✅

These checks are required after the changes to intel_extension_for_transformers/transformers/llm/evaluation/lm_eval/evaluator.py, intel_extension_for_transformers/transformers/llm/quantization/nn/modules.py, intel_extension_for_transformers/transformers/llm/quantization/utils.py, intel_extension_for_transformers/transformers/modeling/modeling_auto.py, intel_extension_for_transformers/transformers/utils/config.py.

🟢 NeuralChat Unit Test

Check ID	Status	Error details
neuralchat-unit-test-baseline	success		✅
neuralchat-unit-test-PR-test	success		✅
Generate-NeuralChat-Report	success		✅

These checks are required after the changes to intel_extension_for_transformers/transformers/llm/quantization/nn/modules.py, intel_extension_for_transformers/transformers/llm/quantization/utils.py, intel_extension_for_transformers/transformers/llm/evaluation/lm_eval/evaluator.py, intel_extension_for_transformers/transformers/modeling/modeling_auto.py, intel_extension_for_transformers/transformers/utils/config.py.

🟢 Engine Unit Test workflow

Check ID	Status	Error details
engine-unit-test-baseline	success		✅
engine-unit-test-PR-test	success		✅
Genreate-Engine-Report	success		✅

These checks are required after the changes to intel_extension_for_transformers/transformers/llm/evaluation/lm_eval/evaluator.py, intel_extension_for_transformers/transformers/llm/quantization/nn/modules.py, intel_extension_for_transformers/transformers/llm/quantization/utils.py, intel_extension_for_transformers/transformers/modeling/modeling_auto.py, intel_extension_for_transformers/transformers/utils/config.py.

🟢 Chat Bot Test workflow

Check ID	Status	Error details
call-inference-llama-2-7b-chat-hf / inference test	success		✅
call-inference-mpt-7b-chat / inference test	success		✅

These checks are required after the changes to intel_extension_for_transformers/transformers/llm/quantization/nn/modules.py, intel_extension_for_transformers/transformers/llm/quantization/utils.py, intel_extension_for_transformers/transformers/llm/evaluation/lm_eval/evaluator.py, intel_extension_for_transformers/transformers/modeling/modeling_auto.py, intel_extension_for_transformers/transformers/utils/config.py.

---

Thank you for your contribution! 💜

Note
This comment is automatically generated and will be updates every 180 seconds within the next 6 hours. If you have any other questions, contact VincyZhang or XuehaoSun for help.

[a32543254]

LGTM

[changwangss]

Intel GPU local validation pass.
itrex pr: #1428
inc pr: intel/neural-compressor#1710
python run_generation_gpu_woq.py --model /mnt/cached_oses/models/Mistral-7B-v0.1 --woq --woq_algo AutoRound --benchmark --calib_len 32 --calib_iter 1 --max_input_length 32 --nsamples 20