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
Installs just this skill. Get the whole plugin for auto-invocation.
⚡ How it fires
How this skill gets triggered: by you, by Claude, or both.
Fires itselfClaude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/optimization-awq
👁️ Context preview
The summary Claude sees to decide when to auto-load this skill.
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
📊 Stats
Stars29,853
Forks3,189
LanguagePython
LicenseMIT
📦 Ships with claude-code-templates
</> SKILL.md
optimization-awq.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 Best Paper Award winner.
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)
**Key insight**: AWQ assumes not all weights are equally important. It protects ~1% of salient weights identified by activation patterns, reducing quantization error without mixed-precision overhead.
## Kernel backends
### GEMM (default, batch inference)
```python
quant_config = {
"zero_point": True,
"q_group_size": 128,
"w_bit": 4,
"version": "GEMM" # Best for batch sizes > 1
}
```
### GEMV (single-token generation)
```python
quant_config = {
"version": "GEMV" # 20% faster for batch_size=1
}
```
**Limitation**: Only batch size 1, not good for large context.
### Marlin (Ampere+ GPUs)
```python
from transformers import AwqConfig, AutoModelForCausalLM
