Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.
安装
npx skills add NVIDIA/skills --skill jetson-inference-mem-tunenpx skills add NVIDIA/skills --skill jetson-inference-mem-tune -a claude-code -gnpx skills add NVIDIA/skills --skill jetson-inference-mem-tune -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/jetson-inference-mem-tunegh skill install NVIDIA/skills jetson-inference-mem-tunegit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/jetson-inference-mem-tune ~/.claude/skills/jetson-inference-mem-tune # Claude Code
cp -R /tmp/NVIDIA__skills/skills/jetson-inference-mem-tune ~/.agents/skills/jetson-inference-mem-tune # Codex, Cursor, Gemini CLI, Copilot, OpenCode