Compression Scaling Laws:Unifying Sparsity and Quantization
We investigate how different compression techniques -- such as weight and activation quantization, and weight sparsity -- affect the scaling behavior of large language models (LLMs) during pretraining. Building on previous work showing that weight sparsity acts as a constant multiplier on model size in scaling laws, we demonstrate that this "effective parameter" scaling pattern extends to quantization as well. Specifically, we establish that weight-only quantization achieves strong parameter efficiency multipliers, while full quantization of both weights and activations shows diminishing returns at lower bitwidths. Our results suggest that different compression techniques can be unified under a common scaling law framework, enabling principled comparison and combination of these methods.
Code (0)
등록된 구현이 없습니다.
Tasks
QuantizationSimilar Papers 제목 키워드 기반
Unifying Two Types of Scaling Laws from the Perspective of Conditional Kolmogorov Complexity
In 2020, OpenAI proposed the first type of Scaling Laws, describing the relationships between model performance and parameters, data, and compute. In 2024, OpenAI proposed the second type of Scaling Laws, describing the …
Scaling Laws for Post Training Quantized Large Language Models
Generalization abilities of well-trained large language models (LLMs) are known to scale predictably as a function of model size. In contrast to the existence of practical scaling laws governing pre-training, the quality…
QuantizationThe case for 4-bit precision: k-bit Inference Scaling Laws
Quantization methods reduce the number of bits required to represent each parameter in a model, trading accuracy for smaller memory footprints and inference latencies. However, the final model size depends on both the nu…
QuantizationScaling Laws for Precision
Low precision training and inference affect both the quality and cost of language models, but current scaling laws do not account for this. In this work, we devise "precision-aware" scaling laws for both training and inf…
QuantizationOn the Expressive Power of Weight Quantization in Large Language Models
In recent years, weight quantization that encodes the learnable parameters of large language models in an $n$-bit format has garnered significant attention due to its potential for model compression and inference acceler…
Model Compression