support fp8 cast WOQ

[xin3he]

Type of Change

feature

Description

https://jira.devtools.intel.com/browse/ILITV-3505
support fp8 cast WOQ using official PyTorch >= 2.2

Expected Behavior & Potential Risk

Torch supports 4 fp8 dtypes as shown below. In INC, we use short strings for mapping.

FP8_MAPPING = {
    "fp8_e5m2": torch.float8_e5m2,
    "fp8_e5m2fnuz": torch.float8_e5m2fnuz,
    "fp8_e4m3fn": torch.float8_e4m3fn,
    "fp8_e4m3fnuz": torch.float8_e4m3fnuz,
}

An introduction to the differences between FP8 data types:
Float8E4M3FN, Float8E4M3FNUZ, Float8E5M2, Float8E5M2FNUZ
stablehlo/rfcs/20230321-fp8_fnuz.md at main · openxla/stablehlo (github.com)

How has this PR been tested?

local test

[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/weight_only/rtn.py, neural_compressor/torch/algorithms/weight_only/utility.py, neural_compressor/torch/quantization/config.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/weight_only/rtn.py, neural_compressor/torch/algorithms/weight_only/utility.py, neural_compressor/torch/quantization/config.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/weight_only/rtn.py, neural_compressor/torch/algorithms/weight_only/utility.py, neural_compressor/torch/quantization/config.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.