_            _    _        _         _
      /\ \         /\ \ /\ \     /\_\      / /\
      \_\ \       /  \ \\ \ \   / / /     / /  \
      /\__ \     / /\ \ \\ \ \_/ / /     / / /\ \__
     / /_ \ \   / / /\ \ \\ \___/ /     / / /\ \___\
    / / /\ \ \ / / /  \ \_\\ \ \_/      \ \ \ \/___/
   / / /  \/_// / /   / / / \ \ \        \ \ \
  / / /      / / /   / / /   \ \ \   _    \ \ \
 / / /      / / /___/ / /     \ \ \ /_/\__/ / /
/_/ /      / / /____\/ /       \ \_\\ \/___/ /
\_\/       \/_________/         \/_/ \_____\/
python-ml-dtypes 0.3.1
Dependencies: eigen-for-python-ml-dtypes@3.4.90-1.7bf2968
Propagated dependencies: python-numpy@1.24.4
Channel: guix-science
Location: guix-science/packages/python.scm (guix-science packages python)
Home page: https://github.com/jax-ml/ml_dtypes
Licenses: ASL 2.0
Synopsis: NumPy dtype extensions used in machine learning
Description:

This package is a stand-alone implementation of several NumPy dtype extensions used in machine learning libraries, including:

  • bfloat16: an alternative to the standard float16 format

  • float8_*: several experimental 8-bit floating point representations including:

    • float8_e4m3b11fnuz

    • float8_e4m3fn

    • float8_e4m3fnuz

    • float8_e5m2

    • float8_e5m2fnuz

  • int4 and uint4: low precision integer types.

Total results: 2