Runs an end-to-end AMD Quark post-training quantization workflow for PyTorch / Hugging Face LLMs: inspect a Hub or local model, choose a quantization plan, create reproducible artifacts, request execution approval, and produce a quantized model. Applies to Llama, Qwen, Mistral, and similar transformer LLM requests involving FP8, INT4, or another Quark scheme.
安装
npx skills add amd/skills --skill quark-torch-llm-ptqnpx skills add amd/skills --skill quark-torch-llm-ptq -a claude-code -gnpx skills add amd/skills --skill quark-torch-llm-ptq -a codex -ggemini skills install https://github.com/amd/skills.git --path skills/quark-torch-llm-ptqgh skill install amd/skills quark-torch-llm-ptqgit clone --depth 1 https://github.com/amd/skills /tmp/amd__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/amd__skills/skills/quark-torch-llm-ptq ~/.claude/skills/quark-torch-llm-ptq # Claude Code
cp -R /tmp/amd__skills/skills/quark-torch-llm-ptq ~/.agents/skills/quark-torch-llm-ptq # Codex, Cursor, Gemini CLI, Copilot, OpenCode