Skill · em Dados, IA e pesquisa
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…
Procedência
- Origem: davila7/claude-code-templates
- Caminho:
cli-tool/components/skills/ai-research/optimization-awq - Versão fixada:
57f899e5394bb8ca166f38eacae8f0853cbfe033 - Licença: MIT
- Espelhado em 25/09/2026
- nenhum download no Claude Code Templates (lido em 25/09/2026)
Antes de instalar
3 arquivos · 23,5 KB · só texto, nenhum script
Instalar na sua CLI
O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.
Claude Code
Neste projeto: instala em .claude/skills/awq-quantization/.
d=".claude/skills/awq-quantization" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/optimization-awq" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/advanced-usage.md" "$u/references/advanced-usage.md" \ -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"
Global: instala em ~/.claude/skills/awq-quantization/.
d="$HOME/.claude/skills/awq-quantization" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/optimization-awq" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/advanced-usage.md" "$u/references/advanced-usage.md" \ -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"
Codex
Neste projeto: instala em .agents/skills/awq-quantization/.
d=".agents/skills/awq-quantization" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/optimization-awq" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/advanced-usage.md" "$u/references/advanced-usage.md" \ -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"
Global: instala em ~/.agents/skills/awq-quantization/.
d="$HOME/.agents/skills/awq-quantization" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/optimization-awq" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/advanced-usage.md" "$u/references/advanced-usage.md" \ -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"
Antigravity
Neste projeto: instala em .agents/skills/awq-quantization/.
d=".agents/skills/awq-quantization" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/optimization-awq" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/advanced-usage.md" "$u/references/advanced-usage.md" \ -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"
Global: instala em ~/.gemini/antigravity-cli/skills/awq-quantization/.
d="$HOME/.gemini/antigravity-cli/skills/awq-quantization" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/optimization-awq" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/advanced-usage.md" "$u/references/advanced-usage.md" \ -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"
Peça ao Rook
Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/cct.awq-quantization
Prévia do SKILL.md
---
name: awq-quantization
description: 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 Be…
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [Optimization, AWQ, Quantization, 4-Bit, Activation-Aware, Memory Optimization, Fast Inference, vLLM Integration, Marlin Kernels]
dependencies: [autoawq, transformers>=4.45.0, torch>=2.0.0]
---
# AWQ (Activation-aware Weight Quantization)
4-bit quantization that preserves salient weights based on activation patterns, achieving 3x speedup with minimal accuracy loss.
## When to use AWQ
**Use AWQ when:**
- Need 4-bit quantization with <5% accuracy loss
- Deploying instruction-tuned or chat models (AWQ generalizes better)
- Want ~2.5-3x inference speedup over FP16
- Using vLLM for production serving
- Have Ampere+ GPUs (A100, H100, RTX 40xx) for Marlin kernel support
**Use GPTQ instead when:**
- Need maximum ecosystem compatibility (more tools support GPTQ)
- Working with ExLlamaV2 backend specifically
- Have older GPUs without Marlin support
**Use bitsandbytes instead when:**
- Need zero calibration overhead (quantize on-the-fly)
- Want to fine-tune with QLoRA
- Prefer simpler integration
## Quick start
### Installation
```bash
# Default (Triton kernels)
pip install autoawq
…