Stand 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.
Install
npx skills add NVIDIA/skills --skill jetson-llm-servenpx skills add NVIDIA/skills --skill jetson-llm-serve -a claude-code -gnpx skills add NVIDIA/skills --skill jetson-llm-serve -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/jetson-llm-servegh skill install NVIDIA/skills jetson-llm-servegit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/jetson-llm-serve ~/.claude/skills/jetson-llm-serve # Claude Code
cp -R /tmp/NVIDIA__skills/skills/jetson-llm-serve ~/.agents/skills/jetson-llm-serve # Codex, Cursor, Gemini CLI, Copilot, OpenCode