Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
安装
npx skills add davila7/claude-code-templates --skill awq-quantizationnpx skills add davila7/claude-code-templates --skill awq-quantization -a claude-code -gnpx skills add davila7/claude-code-templates --skill awq-quantization -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/optimization-awqgh skill install davila7/claude-code-templates awq-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-awq ~/.claude/skills/awq-quantization # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/optimization-awq ~/.agents/skills/awq-quantization # Codex, Cursor, Gemini CLI, Copilot, OpenCode