ai-dynamo/nixl
NVIDIA Inference Xfer Library (NIXL)
About the project
NVIDIA library that accelerates point-to-point data transfers in AI inference frameworks, abstracting over different memory types (CPU, GPU) and storage backends via a plug-in architecture.
Useful for
- Speed up KV-cache exchange between GPU nodes in distributed inference
- Plug in a storage backend (POSIX, GDS, Azure Blob) for cross-node data transfer
- Run nixlbench to measure point-to-point transfer throughput
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 1 star so far today, about 2 expected by the end of the day.
- GitHub Trending C++ today: #13, +1 star.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 1,280
- Today
- 1 · ≈ 2 by evening
- Forks
- 458
- Issues and pull requests
- 2,309
- Watchers
- 27
- Language
- C++
- Latest release
- v1.5.0 · September 30, 2026
- Created
- March 5, 2025
- Last push
- September 30, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 30, 2026GitHub Trending C++ today: #13, +1 star
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/ai-dynamo/nixl)Similar by description
-
1.5
kvcache-ai/Mooncake
LLM serving platform built on a KVCache-centric disaggregated architecture: separates prefill and decode and transfers KV cache between nodes over RDMA. Powers Kimi in production at Moonshot AI.
-
1.8
microsoft/onnxruntime
Cross-platform accelerator for ML inference and training. Runs models from PyTorch, TensorFlow, scikit-learn and others via the ONNX format with graph optimizations and hardware acceleration.