nvidia-ai-iot/jetson-device-skills
9 skills
$npx skills add nvidia-ai-iot/jetson-device-skillsSkillInstalls
jetson-diagnosticRead-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.jetson-headless-modePlan and apply safe Jetson headless-mode changes to reclaim GUI and daemon memory.jetson-inference-mem-tunePick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.jetson-llm-benchmarkBenchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.jetson-llm-serveStand up vLLM or SGLang serving on Jetson, using upstream vLLM on Thor and Orin JetPack 7.2+, and NVIDIA-AI-IOT vLLM on older Orin.jetson-memory-auditMeasure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data.jetson-packagePick Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes; maps Orin SM 8.7 vs Thor SM 11.0 and JetPack-specific package choices.jetson-print-device-infoUse when you need to print Jetson device info (module model, L4T version, kernel, OS version, current power mode) from a running Jetson target.jetson-speculative-decodingAdd EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.