Skip to main content
Ctrl+K
rmm 25.12.00 documentation - Home rmm 25.12.00 documentation - Home
  • User Guide
  • C++ API
  • Python API
  • GitHub
  • X
Home
rmm
cucimcudf-javacudfcugraphcumlcuprojcuspatialcuvscuxfilterdask-cudadask-cudfkvikiolibcudflibcumllibcuprojlibcuspatiallibkvikiolibrapidsmpflibrmmlibucxxraftrapids-cmakerapidsmpfrmmucxx
nightly (25.12)
nightly (25.12)stable (25.10)legacy (25.08)
  • User Guide
  • C++ API
  • Python API
  • GitHub
  • X

Section Navigation

  • rmm (top-level)
  • rmm.mr (Memory Resources)
  • rmm.allocators
  • rmm.statistics
  • rmm.pylibrmm
  • rmm.librmm
  • Python API

Python API#

This page documents the Python API for RMM, imported as the module rmm.

  • rmm (top-level)
    • DeviceBuffer
    • RMMError
    • disable_logging()
    • enable_logging()
    • flush_logger()
    • get_flush_level()
    • get_log_filenames()
    • get_logging_level()
    • is_initialized()
    • level_enum
    • register_reinitialize_hook()
    • reinitialize()
    • set_flush_level()
    • set_logging_level()
    • should_log()
    • unregister_reinitialize_hook()
  • rmm.mr (Memory Resources)
    • ArenaMemoryResource
    • BinningMemoryResource
    • CallbackMemoryResource
    • CudaAsyncMemoryResource
    • CudaAsyncViewMemoryResource
    • CudaMemoryResource
    • DeviceMemoryResource
    • FailureCallbackResourceAdaptor
    • FixedSizeMemoryResource
    • LimitingResourceAdaptor
    • LoggingResourceAdaptor
    • ManagedMemoryResource
    • PinnedHostMemoryResource
    • PoolMemoryResource
    • PrefetchResourceAdaptor
    • SamHeadroomMemoryResource
    • StatisticsResourceAdaptor
    • SystemMemoryResource
    • TrackingResourceAdaptor
    • UpstreamResourceAdaptor
    • available_device_memory()
    • disable_logging()
    • enable_logging()
    • get_current_device_resource()
    • get_current_device_resource_type()
    • get_log_filenames()
    • get_per_device_resource()
    • get_per_device_resource_type()
    • is_initialized()
    • set_current_device_resource()
    • set_per_device_resource()
  • rmm.allocators
    • rmm_cupy_allocator()
    • RMMNumbaManager
  • rmm.statistics
    • ProfilerRecords
    • Statistics
    • enable_statistics()
    • get_statistics()
    • pop_statistics()
    • profiler()
    • push_statistics()
    • statistics()
  • rmm.pylibrmm
    • Overview
    • CUDA Stream Classes
  • rmm.librmm

previous

Namespaces

next

rmm (top-level)

This Page

  • Show Source

© Copyright 2018-2025, NVIDIA Corporation.

Created using Sphinx 8.2.3.

Built with the PyData Sphinx Theme 0.16.1.