
nccl
by NVIDIA (organization)
Optimized primitives for collective multi-GPU communication (description from the project’s GitHub page)
Repository facts
- Stars
- 5,173
- Forks
- 1,446
- Open issues and pull requests
- 452
- Primary language
- C++
- License
- Other license
- Owner
- NVIDIA · Organization
- Created
- Nov 14, 2015
- Last push
- Oct 16, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 770: NVIDIA/cutlass
CUDA Templates and Python DSLs for High-Performance Linear Algebra
10,617 starsC++Other licenseLast push Oct 15, 2026
Rank 2,844: CVCUDA/CV-CUDA
CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.
2,729 starsC++Other licenseLast push Oct 14, 2026
Rank 582: isl-org/Open3D
Open3D: A Modern Library for 3D Data Processing
14,102 starsC++Other licenseLast push Sep 30, 2026
Rank 1,129: NVIDIA/warp
A Python framework for GPU-accelerated simulation, robotics, and machine learning.
7,212 starsPythonApache-2.0Last push Oct 18, 2026
Rank 1,209: flashinfer-ai/flashinfer
FlashInfer: Kernel Library for LLM Serving
6,687 starsCudaApache-2.0Last push Oct 18, 2026
Rank 1,509: NVIDIA/cuml
NVIDIA cuML: GPU-Accelerated Machine Learning
5,306 starsPythonApache-2.0Last push Oct 17, 2026