This is the release note of v5.0.0. See here for the complete list of solved issues and merged PRs.

This release note only covers the difference from v5.0.0rc1; for all highlights and changes, please refer to the release notes of the pre-releases:

• alpha1
• beta1
• beta2
• beta3
• beta4
• RC1

See the Upgrade Guide if you are upgrading from previous versions.

Highlights

• CuPy now supports Python 3.7. Wheel packages are also available.
• Dropped support of CUDA 7.0/7.5. Please update the CUDA installation if you are using these versions.
• Improved compatibility with NumPy 1.15 and SciPy 1.0.

New Features

• Support astype in fused functions (#1705)

Enhancements

• Update ndimage to support SciPy 1.0+ (#1670)
• Reorganize setup requirements (#1696)
• Improve reduction code for performance (#1709)
• Device comparison with non-Device class (#1724)

Bug Fixes

• Fix float16 nextafter (#1676, thanks @toru-fukaya!)
• Fix cupy.random.rand to not generate 1 (#1710)
• Fix comparison with NumPy scalar (#1731)
• Fix ndarray.__iter__ to raise TypeError correctly for 0-d arrays (#1699)

Documentation

• Fix typo in docstring for cupy.linalg.slogdet (#1671, thanks @fiarabbit!)
• Add licenses of distribution kernels from numpy (#1683)
• Add support for NumPy 1.15 in docs (#1729)
• Explain that -ftz=true affects nextafter (#1730)
• Add Python 3.7 support to installation docs (#1742)

Installation

• Update base docker image (#1725)
• Drop support for CUDA 7.0 / 7.5 (#1726)

Tests

• Fix TestRandintDtype was slow (#1693)
• Ignore warning of scipy<1.0 which uses a deprecated feature of numpy>=1.15 (#1708)
• Minor fixes to cupy.random tests (#1712)
• Fix test for Python 3.7 (#1744)

Others

• Add header file generated by Cython to gitignore (#1704)