Agent skill · NVIDIA
dynamo-interconnect-check
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.
What it needs
About 4k tokens when loaded.
What this skill does
Dynamo Interconnect Check <!-- SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. SPDX-License-Identifier: CC-BY-4.0 --> Purpose Confirm that the transport disaggregated serving depends on actually works. A deployment can pass an endpoint smoke test while disagg is silently wrong: if NIXL/UCX cannot reach the peer worker over RDMA or NVLink, KV transfer falls back to a slow or broken path. Catch that with read-only checks before trusting a disagg deployment or its benchmark numbers. This skill is read-only. It never mutates the cluster and never prints secrets. Prerequisites Python 3.10+ on the operator machine. kubectl exec access to a worker pod in the target Dynamo deployment. Read access to the recipe directory (recipes/<model>/<framework>/<mode>). For node-capability checks: tools like ibstat, nvidia-smi, lsmod available in the worker pod image (missing tools are reported as skipped, not failures). When To Use After dynamo-recipe-runner deploys a disagg or multi-node recipe. Before reporting disagg throughput/latency, so numbers reflect the real transport. When agg works but disagg is slow, hangs, or returns wrong output and you suspect the fabric rather than the model. For diagnosing pods that are already crashing or unschedulable, use dynamo-troubleshoot first. Instructions 1. Check Transport Env Vars On The Recipe Reports which NIXL/UCX/NCCL transport variables are set and flags disagg-critical ones (e.g. UCXTLS, UCXNETDEVICES, NCCLIBHCA) that are absent. Missing here is only a warning — they may be baked into the image — so confirm with the node and NIXL checks. See references/interconnect-env-vars.md for what each variable does. 2. Check Node Capabilities Locally on a GPU node, or inside a running worker pod: Probes (read-only) for: InfiniBand devices and Active links, GPUDirect RDMA (nvidiapeermem), GDRCopy, and NVLink in the GPU topology. Missing tools are reported as skipped, not failures. 3. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills NVIDIA/dynamo-interconnect-check