nvidia-nixllisted
Install: claude install-skill air-gapped/skills
# NVIDIA Inference Xfer Library (NIXL)
Target audience: operators wiring NIXL into Dynamo/vLLM/SGLang clusters, plugin authors writing new backends, developers using the agent API directly from Python/C++/Rust. Assumes datacenter-class GPUs (H100/H200/B200/B300) with NVIDIA driver, CUDA 12.8+, RDMA NIC (Mellanox/EFA) for cross-node, and Linux (Ubuntu 22.04/24.04 or Fedora). macOS and Windows are not supported.
## What NIXL is — one paragraph
NIXL is a thin abstraction over heterogeneous transport backends. A `nixlAgent` registers memory regions (DRAM, VRAM, FILE, BLOCK, OBJ), exchanges metadata with peer agents via either ETCD or socket side-channel, then issues asynchronous one-sided `READ`/`WRITE` transfers between local and remote registered memory. The agent picks the best backend (UCX for network, GDS for storage, etc.) based on memory types and what both sides have loaded. Same-process loopback, intra-node GPU-to-GPU, and cross-node RDMA are all the same API. Two operations only — read and write — and both are non-blocking with optional notifications.
## Version snapshot — verify before recommending
| Item | Value | Source |
|---|---|---|
| Latest release | **v1.0.1** (2026-04-14) — maintenance: NIXL-EP destruction/elastic-scale fixes, libfabric thread-safety + notif-on-repost, build/packaging | `gh release list --repo ai-dynamo/nixl` |
| Previous milestone | **v1.0.0** (2026-03-13) — first stable | release notes |
| HEAD pyproject version | **1.1.0** | `pyproject.