3.x SQ supports calib_func for auto-tune

[violetch24]

Type of Change

sq supports calib_func for auto-tune, no need for dataloader

Description

Layer-wise & block-wise enable Add ut check auto-tune Check llm examples

Expected Behavior & Potential Risk

How has this PR been tested?

Dependency Change?

[github-actions[bot]]

🌩️ Required checks status: Pending 🟡

Groups summary

🟡 Code Scan Tests workflow

Check ID	Status	Error details
Code-Scan	no_status		❓
Code-Scan (Bandit Code Scan Bandit)	no_status		❓
Code-Scan (DocStyle Code Scan DocStyle)	no_status		❓
Code-Scan (Pylint Code Scan Pylint)	no_status		❓

These checks are required after the changes to neural_compressor/torch/algorithms/smooth_quant/utility.py.

🟡 Model Tests 3x workflow

Check ID	Status	Error details
Model-Test-3x	no_status		❓
Model-Test-3x (Generate Report GenerateReport)	no_status		❓
Model-Test-3x (Run PyTorch Model opt_125m_woq_gptq_int4)	no_status		❓
Model-Test-3x (Run PyTorch Model opt_125m_woq_gptq_int4_dq_bnb)	no_status		❓
Model-Test-3x (Run PyTorch Model opt_125m_woq_gptq_int4_dq_ggml)	no_status		❓

These checks are required after the changes to neural_compressor/torch/algorithms/smooth_quant/utility.py.

🟡 Unit Tests 3x-PyTorch workflow

Check ID	Status	Error details
UT-3x-Torch	no_status		❓
UT-3x-Torch (Coverage Compare CollectDatafiles)	no_status		❓
UT-3x-Torch (Unit Test 3x Torch Unit Test 3x Torch)	no_status		❓
UT-3x-Torch (Unit Test 3x Torch baseline Unit Test 3x Torch baseline)	no_status		❓

These checks are required after the changes to neural_compressor/torch/algorithms/smooth_quant/utility.py, test/3x/torch/quantization/test_smooth_quant.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 chensuyue or XuehaoSun for help.

[violetch24]

See new design in https://github.com/intel/neural-compressor/pull/1821