Skill · em Dados, IA e pesquisa

hqq-quantization

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.

Procedência

Antes de instalar

3 arquivos · 35,8 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/hqq-quantization/.

d=".claude/skills/hqq-quantization"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/optimization-hqq"
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/hqq-quantization/.

d="$HOME/.claude/skills/hqq-quantization"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/optimization-hqq"
curl -fsSL --create-dirs \
  -o "$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/hqq-quantization/.

d=".agents/skills/hqq-quantization"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/optimization-hqq"
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/hqq-quantization/.

d="$HOME/.agents/skills/hqq-quantization"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/optimization-hqq"
curl -fsSL --create-dirs \
  -o "$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/hqq-quantization/.

d=".agents/skills/hqq-quantization"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/optimization-hqq"
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/hqq-quantization/.

d="$HOME/.gemini/antigravity-cli/skills/hqq-quantization"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/optimization-hqq"
curl -fsSL --create-dirs \
  -o "$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.hqq-quantization

Prévia do SKILL.md

---
name: hqq-quantization
description: 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.
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [Quantization, HQQ, Optimization, Memory Efficiency, Inference, Model Compression]
dependencies: [hqq>=0.2.0, torch>=2.0.0]
---

# HQQ - Half-Quadratic Quantization

Fast, calibration-free weight quantization supporting 8/4/3/2/1-bit precision with multiple optimized backends.

## When to use HQQ

**Use HQQ when:**
- Quantizing models without calibration data (no dataset needed)
- Need fast quantization (minutes vs hours for GPTQ/AWQ)
- Deploying with vLLM or HuggingFace Transformers
- Fine-tuning quantized models with LoRA/PEFT
- Experimenting with extreme quantization (2-bit, 1-bit)

**Key advantages:**
- **No calibration**: Quantize any model instantly without sample data
- **Multiple backends**: PyTorch, ATEN, TorchAO, Marlin, BitBlas for optimized inference
- **Flexible precision**: 8/4/3/2/1-bit with configurable group sizes
- **Framework integration**: Native HuggingFace and vLLM support
- **PEFT compatible**: Fine-tune quantized models with LoRA

**Use alternatives instead:**
- **AWQ**: Need calibration-based accuracy, production serving
- **GPTQ**: Maximum accuracy with calibration data available
- **bitsandbytes**: Simple 8-bit/4-bit without custom backends
- **llama.cpp/GGUF**: CPU inference, Apple Silicon deployment

## Quick start

### Installation
…

Ver todo o marketplace