libcudf-cu12
cuDF - GPU Dataframe (C++)
Decision gist · record as of 2026-08-14
Yes, if you have an NVIDIA GPU with CUDA 12 and need GPU-accelerated tabular data processing. The library is actively maintained, permissively licensed under Apache-2.0, and has no known vulnerabilities. Install friction is moderate (GPU-specific wheels, glibc version constraints, Python 3.11+), but manageable for teams with GPU infrastructure. Most users will install it indirectly as a dependency rather than directly.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires NVIDIA GPU with CUDA 12 support, compatible GPU driver, and Linux system with glibc 2.26+ (aarch64) or 2.27+ (x86_64).
- Python 3.11 or later.
- Medium install friction due to GPU-specific wheel requirements (manylinux_2_26+ and manylinux_2_27+ for aarch64 and x86_64 respectively).
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial and private use with minimal restrictions, making it suitable for production deployments in proprietary systems.
last release 2026-08-06 (8 days) · last repo commit 2026-08-14 · 9,730 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 469,527 downloads/mo, #6,488 on PyPI
Alternatives
Verify before relying
pip install libcudf-cu12
# libcudf-cu12 is a C++ library with 5 runtime dependencies:
# libkvikio-cu12, librmm-cu12, nvidia-libnvcomp-cu12,
# nvidia-nvjitlink-cu12, rapids-logger- Whether libcudf-cu12 can be used directly from Python or requires wrapper libraries for practical usage
- Specific GPU compute capability requirements beyond CUDA 12 availability
- Performance characteristics and typical speedup factors vs. CPU-based alternatives for common operations
What it is and what it does
libcudf-cu12 is the low-level C++ foundation of the RAPIDS GPU data processing suite, providing Apache Arrow-compliant columnar data structures and core algorithms optimized for NVIDIA CUDA 12 GPUs. It handles the heavy lifting for tabular operations—reading, filtering, aggregating, and transforming data—directly on GPU memory, bypassing CPU bottlenecks. The library depends on libkvikio-cu12, librmm-cu12, nvidia-libnvcomp-cu12, nvidia-nvjitlink-cu12, and rapids-logger to function.
The package targets data scientists and engineers working with large tabular datasets who need GPU acceleration. Installation requires a compatible NVIDIA GPU, CUDA 12 runtime, and Linux with specific glibc versions; the wheel distribution is architecture-specific (aarch64 and x86_64). Requires Python 3.11 or later.
Use it for
- Accelerate large-scale data aggregations and groupby operations on GPU for analytics workflows
- Process multi-gigabyte parquet or CSV files faster than CPU alternatives by keeping data on GPU memory
- Build GPU-accelerated ETL pipelines using libraries built on top of libcudf-cu12's core algorithms
- Integrate GPU tabular processing into Spark jobs via plugins built on libcudf-cu12
- Support GPU-native SQL engines and data processing frameworks that depend on libcudf-cu12
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you have an NVIDIA GPU with CUDA 12 and need GPU-accelerated tabular data processing.
The library is actively maintained, permissively licensed under Apache-2.0, and has no known vulnerabilities. Install friction is moderate (GPU-specific wheels, glibc version constraints, Python 3.11+), but manageable for teams with GPU infrastructure. Most users will install it indirectly as a dependency rather than directly.
Install
libcudf-cu12 on PyPI
Before you install
Medium install friction due to GPU-specific wheel requirements (manylinux_2_26+ and manylinux_2_27+ for aarch64 and x86_64 respectively). Active maintenance with recent release (8 days old) and strong repository health (9730 stars, last commit 2026-08-14). Requires Python 3.11+.
Requires NVIDIA GPU with CUDA 12 support, compatible GPU driver, and Linux system with glibc 2.26+ (aarch64) or 2.27+ (x86_64). Python 3.11 or later.
License in practice
Apache-2.0 permissive license allows commercial and private use with minimal restrictions, making it suitable for production deployments in proprietary systems.
Quickstart
pip install libcudf-cu12
# libcudf-cu12 is a C++ library with 5 runtime dependencies:
# libkvikio-cu12, librmm-cu12, nvidia-libnvcomp-cu12,
# nvidia-nvjitlink-cu12, rapids-loggerVerify before relying
- Whether libcudf-cu12 can be used directly from Python or requires wrapper libraries for practical usage
- Specific GPU compute capability requirements beyond CUDA 12 availability
- Performance characteristics and typical speedup factors vs. CPU-based alternatives for common operations
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.11 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 5 packageslibkvikio-cu12librmm-cu12nvidia-libnvcomp-cu12nvidia-nvjitlink-cu12rapids-logger |
| Maintenance | Actively maintained 8 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 469,527 / month, #6,488 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Environment :: GPU :: NVIDIA CUDAIntended Audience :: DevelopersProgramming Language :: C++Topic :: DatabaseTopic :: Scientific/Engineering |
Evidence: libcudf_cu12-26.8.0-py3-none-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl; libcudf_cu12-26.8.0-py3-none-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “gpu accelerated dataframe”
- libcudf-cu12libcudf-cu12 is a GPU-accelerated C++ library providing Apache…
- pylibcudf-cu12pylibcudf-cu12 provides Python bindings for libcudf, a CUDA C++…
- libraft-cu12libraft-cu12 provides CUDA-accelerated primitives and algorithms for…
Give your agent the search over MCP, or paste the wish link into any chat.
More Scientific/Engineering packages
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
pandas provides fast, flexible data structures (Series and DataFrame) for loading, cleaning, transforming, and analyzing labeled or relational data in Python.
scipy provides numerical algorithms for mathematics, science, and engineering—including optimization, integration, linear algebra, Fourier transforms, signal and image processing, and ODE solvers—built on numpy arrays.
scikit-learn provides a comprehensive Python library for supervised and unsupervised machine learning, including classification, regression, clustering, dimensionality reduction, and model evaluation tools built on NumPy and SciPy.
Install it if you need to train, evaluate, or deploy supervised or unsupervised learning models.
dill extends Python's pickle module to serialize and deserialize a much wider range of Python objects, including functions, lambdas, classes, and interpreter sessions, to byte streams for storage or network transmission.
Multiprocess is an enhanced fork of Python's standard multiprocessing library that uses dill for better serialization, allowing you to spawn processes with a threading-like API and share complex objects between them.
Install it if you use multiprocessing and encounter pickle serialization limits with lambdas or complex objects.
See also pylibcudf-cu12 · cudf-cu12 · dask-cudf-cu12 · libraft-cu12 · libucx-cu12 · libcuvs-cu12 · libkvikio-cu12 · librmm-cu12 · raft-dask-cu12 · libcuml-cu12