cuda.core 1.2.1 Release Notes#
New features#
Added Windows on ARM (
win_arm64) wheels. They are provided for CUDA 13 only and for Python 3.11 and newer, and requirecuda.bindings13.4.1 or newer, the first release with Windows on ARM wheels of its own. CPython has no Windows ARM64 build for Python 3.10. All wheels in this release are built against the CUDA 13.4 toolkit, where 1.2.0 used 13.3; the supported CUDA and driver versions are unchanged.
Fixes and enhancements#
system.Device.current_clock_event_reasonsandsystem.Device.supported_clock_event_reasonsnow recognize theBOARD_LIMITandRELIABILITYclock-event reasons that CUDA 13.4 introduced, andsystem.typing.ClocksEventReasonsgained the matching members. Previously, a device that reported either reason made these properties raiseValueErrorfor an unknown reason bit.system.Device.brandnow reports"NVIDIA DLA","NVIDIA vGameDev"and"NVIDIA NPU"for the brand types that CUDA 13.4 introduced, instead of"Unknown".Buffer.from_handle()no longer requires a current CUDA context when the memory resource reportsis_device_accessibleasFalse. Host-only memory records no deallocation stream, so creating and closing such buffers does not call the driver. (#2769)