Deploy, tune, and query vLLM high-throughput inference engines; configure PagedAttention, continuous batching, chunked prefill, and multi-GPU tensor parallelism.
安装
npx skills add alivirgo/Major-AI-Skills --skill vllmnpx skills add alivirgo/Major-AI-Skills --skill vllm -a claude-code -gnpx skills add alivirgo/Major-AI-Skills --skill vllm -a codex -ggemini skills install https://github.com/alivirgo/Major-AI-Skills.git --path skills/vllmgh skill install alivirgo/Major-AI-Skills vllmgit clone --depth 1 https://github.com/alivirgo/Major-AI-Skills /tmp/alivirgo__Major-AI-Skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/alivirgo__Major-AI-Skills/skills/vllm ~/.claude/skills/vllm # Claude Code
cp -R /tmp/alivirgo__Major-AI-Skills/skills/vllm ~/.agents/skills/vllm # Codex, Cursor, Gemini CLI, Copilot, OpenCode