raft logo

raft

NVIDIA/raft

A collection of CUDA-accelerated algorithms for building high-performance machine learning and information retrieval applications.

GraphCanon updated 1d · GitHub synced 1d · 26 views this month

1.0k stars248 forksLast push 2d Cuda Apache-2.0

Decision brief

RAFT is a collection of CUDA-accelerated algorithms for high-performance machine learning and information retrieval applications.

Good fit when

  • - You are developing on an NVIDIA GPU architecture and require optimized, CUDA-accelerated primitives.
  • - The project involves extensive linear algebra operations or vector similarity calculations that would benefit from GPU acceleration.

Avoid when

  • - Your application does not have access to NVIDIA GPUs, as RAFT's algorithms leverage CUDA specifically for performance gains.
  • - If your workload requires more generalized machine learning libraries without a dependency on GPU-accelerated primitives and you are working in a multi-platform or cross-vendor environment.
Requirements:
Ensure access to NVIDIA GPUs; Compatibility with CUDA is essential for utilizing the RAFT algorithms effectively.; The user must have familiarity or develop understanding of CUDA programming to optimize their application integration with RAFT.

Observed Jul 12, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Very active (1d since push)
As of 1d
Provenance
Not a fork · Organization account
As of 1d
Security (OSV)
No lockfile
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Backing

Company context for Nvidia. Display-only - separate from trust and ranking.

Company
NVIDIA Corporation·GitHub org profile·1mo
Employees
11,528·Wikidata (P1128 employees)·1mo
Commercial model
Pure OSS·GitHub org profile (public repos)·1mo

Install

git clone https://github.com/NVIDIA/raft

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

RAFT offers a suite of GPU-accelerated primitives and algorithms crucial for developing high-speed ML models and retrieval systems, utilizing the power of NVIDIA GPUs through CUDA.

Capability facts

Languages
cuda, python

Source: github.language+pyproject.toml · Aug 23, 2026

Categories

Graph entities

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Aug 23, 2026)

In addition being a C++ library, RAFT also provides 2 Python libraries:
Source link

Tags

README

Badge image RAFT: Reusable Accelerated Functions and Tools

RAFT tech stack

Contents


  1. Useful Resources
  2. What is RAFT?
  3. Use cases
  4. Is RAFT right for me?
  5. Getting Started
  6. Installing RAFT
  7. Codebase structure and contents
  8. Contributing
  9. References

Useful Resources

What is RAFT?

RAFT contains fundamental widely-used algorithms and primitives for machine learning and data mining. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.

By taking a primitives-based approach to algorithm development, RAFT

  • accelerates algorithm construction time
  • reduces the maintenance burden by maximizing reuse across projects, and
  • centralizes core reusable computations, allowing future optimizations to benefit all algorithms that use them.

While not exhaustive, the following general categories help summarize the accelerated functions in RAFT:

CategoryAccelerated Functions in RAFT
Data Formatssparse & dense, conversions, data generation
Dense Operationslinear algebra, matrix and vector operations, reductions, slicing, norms, factorization, least squares, svd & eigenvalue problems
Sparse Operationslinear algebra, eigenvalue problems, slicing, norms, reductions, factorization, symmetrization, components & labeling
Solverscombinatorial optimization, iterative solvers
Statisticssampling, moments and summary statistics, metrics, model evaluation
Tools & Utilitiescommon tools and utilities for developing CUDA applications, multi-node multi-gpu infrastructure

RAFT is a C++ header-only template library with an optional shared library that

  1. can speed up compile times for common template types, and
  2. provides host-accessible "runtime" APIs, which don't require a CUDA compiler to use

In addition being a C++ library, RAFT also provides 2 Python libraries:

  • pylibraft - lightweight Python wrappers around RAFT's host-accessible "runtime" APIs.
  • raft-dask - multi-node multi-GPU communicator infrastructure for building distributed algorithms on the GPU with Dask.

Is RAFT right for me?

RAFT contains low-level primitives for accelerating applications and workflows. Data source providers and application developers may find specific tools very useful. RAFT is not intended to be used directly by data scientists for discovery and experimentation. For data science

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.