.. currentmodule:: cuda.core.experimental
Released on MM DD, 2025
- Starting this release
cuda.coreis licensed under Apache 2.0. - Initial support for CUDA graphs (phase 1).
- In this release, we support building a CUDA graph that captures kernel launches. The captured graph can be replayed to reduce latency. Graph split/join and conditional nodes are supported.
- :class:`Kernel` adds :attr:`Kernel.num_arguments` and :attr:`Kernel.arguments_info` for introspection of kernel arguments. (#612)
- Add pythonic access to kernel occupancy calculation functions via :attr:`Kernel.occupancy`. (#648)
- Support launching cooperative kernels by setting :attr:`LaunchConfig.cooperative_launch` to True.
- A name can be assigned to :class:`ObjectCode` instances generated by both :class:`Program` and :class:`Linker` through their respective options.
- Look-up of the :attr:`Event.device` and :attr:`Event.context` (the device and CUDA context where an event was created from) is now possible.
- The :func:`launch` function's handling of fp16 scalars was incorrect and is fixed.
- The :class:`Device` constructor is made faster.