Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.
安装
npx skills add davila7/claude-code-templates --skill hqq-quantizationnpx skills add davila7/claude-code-templates --skill hqq-quantization -a claude-code -gnpx skills add davila7/claude-code-templates --skill hqq-quantization -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/optimization-hqqgh skill install davila7/claude-code-templates hqq-quantizationgit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/optimization-hqq ~/.claude/skills/hqq-quantization # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/optimization-hqq ~/.agents/skills/hqq-quantization # Codex, Cursor, Gemini CLI, Copilot, OpenCode