Migrate RTN, HQQ and AWQ to Torch new 3.x API

[yuwenzho]

Type of Change

feature
API changed or not: yes

Description

Migrate RTN, HQQ and AWQ to Torch new 3x API

RTN

from neural_compressor.torch.quantization import get_default_rtn_config, prepare, convert
quant_config = get_default_rtn_config()
model= prepare(model, quant_config)
q_model = convert(model)

HQQ

from neural_compressor.torch.quantization import get_default_hqq_config, prepare, convert
quant_config = get_default_hqq_config()
model= prepare(model, quant_config)
q_model = convert(model)

AWQ

from neural_compressor.torch.quantization import get_default_awq_config, prepare, convert
quant_config = get_default_awq_config()
# prepare
model= prepare(model, quant_config, example_inputs=example_inputs)
# calibrate
calib_func(model)
# convert
q_model = convert(model)

How has this PR been tested?

CI

Dependency Change?

no

[github-actions]

⚡ Required checks status: All passing 🟢

Groups summary

🟢 Code Scan Tests workflow

Check ID	Status	Error details
Code-Scan	success		✅
Code-Scan (Bandit Code Scan Bandit)	success		✅
Code-Scan (DocStyle Code Scan DocStyle)	success		✅
Code-Scan (Pylint Code Scan Pylint)	success		✅

These checks are required after the changes to neural_compressor/torch/algorithms/base_algorithm.py, neural_compressor/torch/algorithms/static_quant/static_quant.py, neural_compressor/torch/algorithms/weight_only/awq.py, neural_compressor/torch/algorithms/weight_only/hqq/__init__.py, neural_compressor/torch/algorithms/weight_only/hqq/quant_api.py, neural_compressor/torch/algorithms/weight_only/hqq/quantizer.py, neural_compressor/torch/algorithms/weight_only/rtn.py, neural_compressor/torch/algorithms/weight_only/utility.py, neural_compressor/torch/quantization/algorithm_entry.py.

🟢 Model Tests 3x workflow

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

These checks are required after the changes to neural_compressor/torch/algorithms/base_algorithm.py, neural_compressor/torch/algorithms/static_quant/static_quant.py, neural_compressor/torch/algorithms/weight_only/awq.py, neural_compressor/torch/algorithms/weight_only/hqq/__init__.py, neural_compressor/torch/algorithms/weight_only/hqq/quant_api.py, neural_compressor/torch/algorithms/weight_only/hqq/quantizer.py, neural_compressor/torch/algorithms/weight_only/rtn.py, neural_compressor/torch/algorithms/weight_only/utility.py, neural_compressor/torch/quantization/algorithm_entry.py.

🟢 Unit Tests 3x-PyTorch workflow

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

These checks are required after the changes to neural_compressor/torch/algorithms/base_algorithm.py, neural_compressor/torch/algorithms/static_quant/static_quant.py, neural_compressor/torch/algorithms/weight_only/awq.py, neural_compressor/torch/algorithms/weight_only/hqq/__init__.py, neural_compressor/torch/algorithms/weight_only/hqq/quant_api.py, neural_compressor/torch/algorithms/weight_only/hqq/quantizer.py, neural_compressor/torch/algorithms/weight_only/rtn.py, neural_compressor/torch/algorithms/weight_only/utility.py, neural_compressor/torch/quantization/algorithm_entry.py, test/3x/torch/quantization/weight_only/hqq/test_hqq_cpu.py, test/3x/torch/quantization/weight_only/hqq/test_hqq_cuda.py, test/3x/torch/quantization/weight_only/test_awq.py, test/3x/torch/quantization/weight_only/test_rtn.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.

[yiliu30]

Others are LTGM.