NVIDIA/nvshmem

View on GitHub

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.

Stars: 586
Forks: 110
Open beginner issues: 0
Indexed issues: 20

Dominant language: C++
License: Apache-2.0
Last GitHub push: Aug 27, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Beginner friendly Everything

Open All

20 open issues indexed

nvshmem4py: test_get_on_tensor cannot fail and never performs a remote read Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

NVIDIA/nvshmem#108 · Opened Sep 18, 2026
numba-cuda-mlir: device-library linking input is unobtainable from source on CUDA 12.8 (sm_90 LTOIR only, no LLVM) Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

NVIDIA/nvshmem#107 · Opened Sep 18, 2026
CuTe collective proxy timeout on PCIe: L20 capability data, and float32 reduce/sum does not reproduce on 3.7.2 Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

NVIDIA/nvshmem#103 · 2 comments · Opened Sep 18, 2026
[Question]: No more teams available Open

question

Difficulty 4/5 3-5 days Newbie friendliness 38/100

NVIDIA/nvshmem#100 · 3 comments · Opened Aug 3, 2026
[Roadmap]: NVSHMEM Roadmap Q3 2026 Open

roadmap

Difficulty 5/5 Over a week Newbie friendliness 30/100

NVIDIA/nvshmem#95 · 2 comments · 2 reactions · Opened Jun 29, 2026
[Question]: Is efa-dp-direct integration planned as a GPU-initiated transport for libfabric/EFA? Open

question

Difficulty 5/5 Over a week Newbie friendliness 30/100

NVIDIA/nvshmem#87 · 7 comments · Opened May 11, 2026
[Question]: Repeated stream creation during initialization phase Open

question

Difficulty 4/5 3-5 days Newbie friendliness 45/100

NVIDIA/nvshmem#77 · 2 comments · Opened Mar 26, 2026
[Question]: How does nvshmem_signal_wait_until guarantee data visibility? Open

question

Difficulty 4/5 3-5 days Newbie friendliness 35/100

NVIDIA/nvshmem#75 · Opened Mar 23, 2026
[Question]: Data consistency across multiple devices in P2P scenarios Open

question

Difficulty 4/5 3-5 days Newbie friendliness 18/100

NVIDIA/nvshmem#73 · 1 comment · Opened Mar 18, 2026
[Question]: Publications.md Open

question

Difficulty 3/5 1-2 days Newbie friendliness 45/100

NVIDIA/nvshmem#72 · 2 comments · Opened Mar 17, 2026
[RFE]: Is it possible to support CM connection establishment on NVSHMEM Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 30/100

NVIDIA/nvshmem#65 · 1 comment · 1 reaction · Opened Feb 28, 2026
[RFE]: infiniband counters are needed to help diagnose the issue Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 25/100

NVIDIA/nvshmem#64 · 2 comments · 1 reaction · Opened Feb 27, 2026
[Issue]: CMake Build Issue on 3.5.19. Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

NVIDIA/nvshmem#54 · 3 comments · Opened Jan 20, 2026
[Issue]: IB env will fail if export NVSHMEM_IB_TRAFFIC_CLASS Open

Difficulty 4/5 3-5 days Newbie friendliness 30/100

NVIDIA/nvshmem#45 · 4 comments · Opened Dec 10, 2025
[RFE]: Need more detailed log when creating QPs Open

enhancement

Difficulty 3/5 1-2 days Newbie friendliness 48/100

NVIDIA/nvshmem#42 · 1 comment · Opened Dec 1, 2025
[Issue]: cannot build NVSHMEM examples with clang Open

bug

NVIDIA/nvshmem#29 · 1 comment · 1 assignee · Opened Nov 14, 2025
[Issue]: ibgda over RoCE v2 Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 35/100

NVIDIA/nvshmem#27 · 2 comments · 1 reaction · Opened Nov 11, 2025
[Question]: In the ibgda_poll_cq function, only the first CQE is used. Open

question

Difficulty 5/5 Over a week Newbie friendliness 25/100

NVIDIA/nvshmem#20 · Opened Oct 29, 2025
[Issue]: Failed to run reduction_latency across nodes using ibrc Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 35/100

NVIDIA/nvshmem#16 · 9 comments · Opened Oct 13, 2025
[PerfTests] `--msgrate` flag causes runtime exception Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 28/100

NVIDIA/nvshmem#5 · 1 comment · Opened Sep 11, 2025

NVIDIA/nvshmem

Get new issues in your inbox