jetson-print-device-info

par nvidia

Utilisez lorsque vous devez imprimer les informations du périphérique Jetson (modèle du module, version L4T, noyau, version du système d'exploitation, mode d'alimentation actuel) à partir d'une cible Jetson en cours d'exécution. Il s'agit d'un…

npx skills add https://github.com/nvidia/skills --skill jetson-print-device-info

jetson-print-device-info

Prints a concise summary of the Jetson device this skill runs on.

This skill is intended as a reference example for the jetson-device-skills repo and the NVIDIA-wide skills CI. It runs on the Jetson target (not the host PC) and performs read-only inspection — useful as a baseline capture before running performance tests.

Purpose

Capture a baseline snapshot of a Jetson target's software stack and power mode before running performance, regression, or compatibility tests.

When to use

  • Starting a performance run and you want a captured baseline of the device's software stack and power mode.
  • Verifying that a freshly flashed Jetson matches an expected L4T / JetPack version.

Prerequisites

  • Running on a Jetson target (not the host PC).
  • Standard CLIs available: tr, cat, uname, uptime, lsb_release (or /etc/os-release).
  • nvpmodel available for power mode (optional — skill falls back gracefully).

Inputs

None. The skill reads only from the local Jetson filesystem and standard CLIs.

Instructions

Run each step in order and print the captured values into the report shown under Output format.

  1. Capture the module model and validate it is a Jetson target — exit early otherwise:
    # Device-tree strings are null-terminated, so strip NULs before printing.
    model=$(tr -d '\0' < /proc/device-tree/model 2>/dev/null)
    case "$model" in
      *Jetson*) ;;
      *) echo "Not running on a Jetson target (model: '${model:-unknown}')"; exit 1 ;;
    esac
    echo "$model"
    
  2. Extract the L4T release header line — skip the rest of the file (long list of library SHAs):
    head -1 /etc/nv_tegra_release 2>/dev/null || echo "L4T release info not found"
    # Equivalent: grep -m1 '^# R' /etc/nv_tegra_release
    
  3. Run nvpmodel -q and join its two output lines (NV Power Mode: <name> and the mode number) onto one line. paste -sd only uses the first char of its delimiter, so use awk to insert the literal / separator:
    nvpmodel -q 2>/dev/null | awk 'NR==1{a=$0; next} {print a" / "$0}' \
      || echo "nvpmodel not available"
    
  4. Print the kernel version and uptime:
    uname -r
    uptime -p
    
  5. Print the OS version (prefer lsb_release, fall back to /etc/os-release):
    lsb_release -ds 2>/dev/null || (. /etc/os-release && echo "$PRETTY_NAME") || echo "OS version not found"
    

Output format

Print a short report with these sections, one line each where possible:

Model:           <device-tree model string>
L4T release:     <release header line>
Power mode:      <nvpmodel name> / <mode number>
Kernel:          <uname -r>
Uptime:          <uptime -p>
OS version:      <lsb_release / /etc/os-release output>

Examples

Example output on an Orin AGX dev kit (L4T R36 / Ubuntu 22.04):

Model:           NVIDIA Jetson AGX Orin Developer Kit
L4T release:     # R36 (release), REVISION: 3.0
Power mode:      NV Power Mode: MAXN / 0
Kernel:          5.15.136-tegra
Uptime:          up 2 hours, 14 minutes
OS version:      Ubuntu 22.04.4 LTS

Example output on an AGX Thor (L4T R39 / Ubuntu 24.04):

Model:           NVIDIA Jetson AGX Thor Developer Kit
L4T release:     # R39 (release), REVISION: 0.0
Power mode:      NV Power Mode: 120W / 1
Kernel:          6.8.0-tegra
Uptime:          up 12 minutes
OS version:      Ubuntu 24.04 LTS

Error handling

Each command falls back to a clearly labeled "... not found" / "... not available" string if the underlying file or binary is missing — the skill never errors out mid-report. If /proc/device-tree/model is missing or does not contain a Jetson string, exit early with a clear "not running on a Jetson target" message.

Limitations

  • Read-only inspection only — does not detect GPU/CPU clocks, thermal state, or per-rail power.
  • nvpmodel output format varies between L4T versions; the skill prints it verbatim rather than parsing.

Troubleshooting

  • Error: /proc/device-tree/model: No such file or directory Cause: Running on a host PC, not a Jetson target. Solution: Run the skill on the Jetson device directly (e.g. via SSH).

  • Error: nvpmodel: command not found Cause: L4T BSP not installed, or running in a minimal container without nvpmodel. Solution: Expected on non-Jetson or stripped environments — the skill prints "nvpmodel not available" and continues.

Notes

  • Read-only. Do not change power mode, install packages, or modify any files.
  • If the skill is invoked on a host PC by mistake, /proc/device-tree/model will not contain a Jetson model string — detect that and exit with a clear message rather than printing misleading info.

Plus de skills de nvidia

compileiq-debug
nvidia
Utilisez quand quelque chose ne va pas : Search() bloque, toutes les évaluations retournent INVALID_SCORE, les scores ne s'améliorent pas, chaque configuration retourne le même nombre, erreurs ptxas…
create-github-pr
nvidia
Créer des pull requests GitHub en utilisant l'interface en ligne de commande gh. Utiliser lorsque l'utilisateur souhaite créer une nouvelle PR, soumettre du code pour révision, ou ouvrir une pull request. Mots-clés de déclenchement -…
nemoclaw-maintainer-cross-issue-sweep
nvidia
Analyse les autres problèmes ouverts pour trouver ceux qu’une PR donnée pourrait également corriger ou casser accidentellement. Génère des opportunités de correctifs adjacents et des risques de contradiction avec fichier:ligne…
fhir-basics
nvidia
Apprend aux agents comment fonctionnent les API FHIR R4, quelles ressources sont disponibles, comment les interroger avec des paramètres de recherche, et comment analyser correctement tous les formats de réponse…
compileiq-validate-result
nvidia
Utiliser APRÈS qu'une recherche soit terminée et AVANT de réclamer un accélérateur ou d'expédier un ACF. Charge le CSV dump_results, extrait les K meilleurs candidats (mono-objectif)…
changelog-audit
nvidia
Auditer le CHANGELOG.md de Warp avant une publication : récupérer les entrées perdues, trier par impact utilisateur, affiner le langage des entrées, ajuster les retours à la ligne et (en mode branche de publication) mettre à jour la comparaison…
maintain-dynamic-plugins
nvidia
Maintenir les chargeurs de plugins dynamiques NeMo Relay, les manifestes, les SDK natifs Rust, le protocole worker gRPC, le SDK worker Python, la documentation, les tests et la couverture du workflow de publication
dgx-diagnose
nvidia
Diagnostiquer les problèmes courants du DGX Station GB300 — plantages CUDA, ciblage incorrect du GPU, bugs de conteneur vLLM/SGLang, problèmes d'état MIG, erreurs NVLink/Fabric Manager,…