Home Projects nccl
nccl
C++

nccl

Optimized primitives for collective multi-GPU communication

by NVIDIA · GitHub
Stars
Forks
Created
Last commit
Language
communicationscppcudaC++
View on GitHub
In plain words

Facilitate communication between multiple graphics cards in your computer for faster processing tasks.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
nccl — GitHub preview card
📈 Star history
4.9k4.8k
2026-07-042026-08-31
📈 Track nccl

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Optimized primitives for collective multi-GPU communication

nccl has 4.9k stars on GitHub. It has been forked 1.3k times. nccl is written mainly in C++. It has been in active development since 2015. Its main topics are communications, cpp, cuda, deep-learning.

Frequently asked questions

What is nccl?

Optimized primitives for collective multi-GPU communication

Is nccl open source?

nccl is an open-source project.

Is nccl free?

Yes. nccl is free and open source — you can use, modify and self-host it.

What language is nccl written in?

nccl is written mainly in C++.

🏅 Maintainer of this project?
olud.ai badge — nccl

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=nvidia-nccl)](https://olud.ai/project/nvidia-nccl.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.