ai-agent

RAFT: Accelerate Machine Learning

Name: RAFT: Accelerate Machine Learning
Author: NVIDIA

Get building blocks for high performance ML apps with RAFT, used by developers with 1.0k+ GitHub stars.

1,028 stars241 forksCudaQuality 8/10Updated 7/17/2026100% free · open source

What it does

RAFT provides building blocks for high performance machine learning applications, including fundamental algorithms and primitives, to help developers write efficient apps more easily

Install / run

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

When to use it

•When building a high-performance machine learning application that requires GPU acceleration
•When needing widely-used algorithms and primitives for machine learning and information retrieval
•When developing applications that require CUDA-accelerated computations

Quick start

1Navigate to the cloned repository: `cd raft`
2Build the RAFT library using the provided build script: `mkdir build && cd build && cmake .. && make`
3Explore the example applications in the `examples` directory to see how to use RAFT in your own project
4Refer to the `README.md` file for more detailed instructions on building and using RAFT
5Use the `raft` library in your own C++ project by including the `raft/include` directory and linking against the `raft/lib` directory

Ready-to-paste prompt

To build and run the RAFT example application, use the command: `cd build && cmake .. && make && ./examples/raft_example`

Heads up: RAFT requires a CUDA-compatible NVIDIA GPU to function, so ensure you have a supported GPU installed and the CUDA toolkit is properly configured on your system

Saves to your device