nvidia-nixl SKILL.md skillA
nvidia-nixl from air-gapped/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add air-gapped/skills/nvidia-nixl@git:20261027.53a56aePins git:20261027.53a56ae in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- air-gapped/skills
- Path
.claude/skills/nvidia-nixl/SKILL.md- Versions recorded
- 11
- Latest version
- git:20261027.45593a3, committed Oct 27, 2026
- First version recorded
- May 29, 2026
- Size
- 20,926 bytes
- Repository stars
- 6
- License
- MIT
NVIDIA Inference Xfer Library (NIXL) operator + developer reference. Point-to-point KV-cache and tensor transport for distributed inference (Dynamo, vLLM, SGLang). Covers the agent API (full Python reference; C++/Rust via upstream pointers), all 15 backend plugins (UCX, GDS, GDS_MT, libfabric, mooncake, posix, hf3fs, obj/S3, azure_blob, infinia/DDN, gusli, uccl, gpunetio/DOCA, telemetry, tracing), AMD ROCm/HIP support, build paths (pip nixl-cu12/cu13, meson+ninja from source), ETCD vs…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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 (`references/python-api.md`). C++/Rust developers: consult `src/api/cpp/` headers and `examples/{cpp,rust}/` upstream directly — this skill does not carry a C++/Rust API reference. 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 the *transport*, not a cache. If the goal is a KV cache that outlives a
single vLLM process, the thing being configured is **`lmcache-mp`** (same
`inference-cache` plugin) — a standalone LMCache server that can use NIXL as one
of its backends. Come here for the agent API, plugins, and wire-level
behaviour; go there for the cache server's deployment, sizing, and ZMQ wiring.
…Read the whole file at its exact version.
How to install
mdr add air-gapped/skills/nvidia-nixl@sha256:dd9a5e8c2a7efc79The line at the top of this page pins the label git:20261027.53a56ae, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_6lw3dgx26f3pgenh)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 11 versions of this file, between May 29, 2026 and Oct 27, 2026, about one every 15 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261027.45593a3 latest | 2026-10-27 | 45593a3 | 20,926 B | A | view · diff |
| git:20261027.53a56ae | 2026-10-27 | 53a56ae | 20,490 B | A | view · diff |
| git:20261027.5ea85d0 | 2026-10-27 | 5ea85d0 | 20,921 B | A | view · diff |
| git:20261027.64bf80d | 2026-10-27 | 64bf80d | 20,375 B | A | view · diff |
| git:20261027.dc50285 | 2026-10-27 | dc50285 | 20,964 B | A | view · diff |
| git:20260922.5e8f509 | 2026-09-22 | 5e8f509 | 20,104 B | A | view · diff |
| git:20260915.34767df | 2026-09-15 | 34767df | 20,049 B | A | view · diff |
| git:20260818.36f6464 | 2026-08-18 | 36f6464 | 20,019 B | A | view · diff |
| git:20260725.aef8f18 | 2026-07-25 | aef8f18 | 19,962 B | A | view · diff |
| git:20260721.e5d9d1a | 2026-07-21 | e5d9d1a | 19,575 B | A | view · diff |
| git:20260529.3ea3e45 | 2026-05-29 | 3ea3e45 | 16,280 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (20926 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
air-gapped/skills · 6 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6lw3dgx26f3pgenh GET https://markdownregistry.com/api/v1/resolve?ref=air-gapped/skills/nvidia-nixl GET https://markdownregistry.com/api/v1/blob/dd9a5e8c2a7efc79a7932d82bb534e5205d9cb3b8dea4356cec54d306387fd86
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.