awq-quantization
NewActivation-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.
Install & Usage
mkdir -p .claude/skillsmkdir -p .claude/skills && curl -o .claude/skills/awq-quantization.md https://raw.githubusercontent.com/davila7/claude-code-templates/main/cli-tool/components/skills/ai-research/optimization-awq/SKILL.md/awq-quantizationFrequently Asked Questions
What is awq-quantization?
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.
How to install awq-quantization?
To install awq-quantization, create the .claude/skills directory in your project, then run the curl command to download the skill file. Once installed, invoke it in Claude Code with /awq-quantization.
What is awq-quantization best for?
awq-quantization is a community categorized under General. It is designed for: deployment, ai-&-ml, data-&-analytics. Created by davila7.