Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).
安装
npx skills add NVIDIA/skills --skill rag-perfnpx skills add NVIDIA/skills --skill rag-perf -a claude-code -gnpx skills add NVIDIA/skills --skill rag-perf -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/rag-perfgh skill install NVIDIA/skills rag-perfgit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/rag-perf ~/.claude/skills/rag-perf # Claude Code
cp -R /tmp/NVIDIA__skills/skills/rag-perf ~/.agents/skills/rag-perf # Codex, Cursor, Gemini CLI, Copilot, OpenCode