GitHub - seculayer/AutoAPE-Quant

Post-Training Quantization
- DynamicQuantization(8 bit)
- IntegerQuantization(8 bit)
- Float16Quantization(16 bit)
Quantization-Aware Training(8 bit)

Name		Name	Last commit message	Last commit date
Latest commit History 2 Commits
DynamicQuantizationConverter.py		DynamicQuantizationConverter.py
Float16QuantizationConverter.py		Float16QuantizationConverter.py
IntegerQuantizationConverter.py		IntegerQuantizationConverter.py
QATQuantizationConverter.py		QATQuantizationConverter.py
QuantizationConverter.py		QuantizationConverter.py
README.md		README.md
load_dataset.py		load_dataset.py
poetry.lock		poetry.lock
pyproject.toml		pyproject.toml

Provide feedback