Register pt2e static quantization

[yiliu30]

Type of Change

feature or bug fix or documentation or validation or others
API changed or not

Description

Register pt2e static quantization

• Align the W8A8StaticQuantizer with Quantizer
• Add export API
• Map the StaticQuantConfig to X86InductorQuantizer's config
• Add export for ipex by separate PR

Usage

# User script
model = UserModel()
example_inputs = ...

# quantize script

# import intel_extension_for_pytorch ### <--- if user want to use ipex' static quant

from neural_compressor.torch.quantization import get_default_static_config, prepare, convert
from neural_compressor.torch.export import export

# export
dynamic_shapes = {"input_ids": (None, Dim("seq_len"))}
exported_model = export(model, example_inputs=example_inputs, dynamic_shapes=dynamic_shapes)

# prepare
quant_config = get_default_static_config()
prepare_model = prepare(model, quant_config)

# calibrate
run_fn(prepare_model)

# convert
converted_model = convert(prepare_model)

# compile and inference
opt_model = torch.compile(converted_model)
out = opt_model(*example_inputs)

@ftian1 @xin3he @violetch24

How has this PR been tested?

Pre-CI

Dependency Change?

None

[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/pt2e_quant/__init__.py, neural_compressor/torch/algorithms/pt2e_quant/core.py, neural_compressor/torch/export/__init__.py, neural_compressor/torch/export/_export.py, neural_compressor/torch/quantization/algorithm_entry.py, neural_compressor/torch/quantization/config.py, neural_compressor/torch/utils/constants.py, neural_compressor/torch/utils/environ.py, neural_compressor/torch/utils/utility.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/pt2e_quant/__init__.py, neural_compressor/torch/algorithms/pt2e_quant/core.py, neural_compressor/torch/export/__init__.py, neural_compressor/torch/export/_export.py, neural_compressor/torch/quantization/algorithm_entry.py, neural_compressor/torch/quantization/config.py, neural_compressor/torch/utils/constants.py, neural_compressor/torch/utils/environ.py, neural_compressor/torch/utils/utility.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/pt2e_quant/__init__.py, neural_compressor/torch/algorithms/pt2e_quant/core.py, neural_compressor/torch/export/__init__.py, neural_compressor/torch/export/_export.py, neural_compressor/torch/quantization/algorithm_entry.py, neural_compressor/torch/quantization/config.py, neural_compressor/torch/utils/constants.py, neural_compressor/torch/utils/environ.py, neural_compressor/torch/utils/utility.py, test/3x/torch/algorithms/pt2e_quant/test_pt2e_w8a8.py, test/3x/torch/quantization/test_pt2e_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.

[chensuyue]

@xin3he please review.