NVIDIA/nvshmem

nvshmem

✅ Recently maintained

NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process communication and coordination overheads by allowing programmers to perform one-sided communication from within CUDA kernels and on CUDA streams.

602Stars
116Forks
+67-day stars

C++ · Apache-2.0 · Last push 2026-10-28

Official repository & installation ↗
communciationscppcudadeep-learningnvidiapython

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2025-09-292026-11-02
View historical data
DateStars
2026-10-04592
2026-10-05592
2026-10-06593
2026-10-07594
2026-10-08595
2026-10-09595
2026-10-10595
2026-10-11595
2026-10-12595
2026-10-13595
2026-10-14595
2026-10-15595
2026-10-16595
2026-10-17595
2026-10-18595
2026-10-19595
2026-10-20595
2026-10-21595
2026-10-22595
2026-10-23595
2026-10-24596
2026-10-25596
2026-10-26596
2026-10-27596
2026-10-28599
2026-10-29599
2026-10-30600
2026-10-31600
2026-11-01600
2026-11-02602

Get the project

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

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.