{"categories":[{"label":"Scientific/Engineering","url":"https://skillfed.io/packages/category/scientific-engineering/4"},{"label":"Database","url":"https://skillfed.io/packages/category/database/3"}],"enrichment":{"capability":"RMM provides a common interface for customizing GPU and host memory allocation, with implementations for device memory pooling, pinned host memory, and other allocation strategies.","skillfed_tags":["gpu-memory-management","cuda","rapids"],"use_cases":["Reduce GPU memory allocation overhead in tight loops by using a device memory pool sub-allocator.","Enable asynchronous host-to-device transfers by allocating pinned host memory through RMM.","Integrate custom memory allocation strategies into RAPIDS libraries like cuDF or cuML.","Profile and optimize memory usage patterns in GPU-accelerated data processing pipelines.","Build C++ applications that need portable, customizable GPU memory management across different NVIDIA architectures."],"what_it_does":"RMM is a memory management library for GPU-accelerated workflows that sits between your application and CUDA's memory allocator. It provides a pluggable interface for customizing how device memory and host memory are allocated, enabling strategies like device memory pooling (to reduce allocation overhead) and pinned host memory (for faster asynchronous transfers). The library is part of the RAPIDS ecosystem and is designed for applications that need fine-grained control over memory behavior to achieve optimal GPU performance.\n\nThe package depends on cuda-bindings, librmm-cu12 (the compiled C++ library), and numpy. Installation requires a CUDA 12.2+ environment and works with Python 3.11 through 3.14. It is actively maintained and has no known security vulnerabilities.","worth_installing":"Yes, if you are building GPU-accelerated applications with CUDA 12.2+ and need to optimize memory allocation behavior. The active maintenance, permissive license, and zero known vulnerabilities make it a safe choice. Install friction is moderate due to compiled dependencies and CUDA requirements, but this is expected for GPU libraries. Not necessary for simple GPU workloads that do not require custom memory strategies."},"id":"rmm-cu12","links":{"html":"https://skillfed.io/packages/rmm-cu12","md":"https://skillfed.io/packages/rmm-cu12.md","pypi":"https://pypi.org/project/rmm-cu12/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-08-06","license_spdx":"Apache-2.0","license_treatment":"permissive","name":"rmm-cu12","python_support":"supports_current","summary":"rmm - RAPIDS Memory Manager"},"popularity":{"monthly_downloads":429944,"position":6736,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"26.8.0"}