An implementation of generic floating point encode/decode logic, handling various current and proposed floating point types:
- IEEE 754: Binary16, Binary32
- OCP Float8: E5M2, E4M3
- IEEE WG P3109: P{p} for p in 1..7
See https://gfloat.readthedocs.io for documentation.
pip install -e .
cd docs
make html
cd ..
rm -rf dist
pip install build twine
python -m build
echo __token__ | twine upload --repository pypi dist/* --verbose
All NaNs are the same, with no distinction between signalling or quiet, or between differently encoded NaNs.