Serves an LLM on a supported AMD EPYC server CPU using vLLM with zentorch, in Docker, Podman, or conda. Use for "vLLM on CPU", "zentorch serving", or an EPYC CPU endpoint, including on a host that also has AMD Instinct GPUs. Detects the EPYC generation, validates the runtime, checks model support and RAM fit, sizes threads/KV/NUMA, confirms the plan, launches, and verifies the endpoint.
安装
npx skills add amd/skills --skill serving-llms-on-epycnpx skills add amd/skills --skill serving-llms-on-epyc -a claude-code -gnpx skills add amd/skills --skill serving-llms-on-epyc -a codex -ggemini skills install https://github.com/amd/skills.git --path skills/serving-llms-on-epycgh skill install amd/skills serving-llms-on-epycgit clone --depth 1 https://github.com/amd/skills /tmp/amd__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/amd__skills/skills/serving-llms-on-epyc ~/.claude/skills/serving-llms-on-epyc # Claude Code
cp -R /tmp/amd__skills/skills/serving-llms-on-epyc ~/.agents/skills/serving-llms-on-epyc # Codex, Cursor, Gemini CLI, Copilot, OpenCode