相关论文: A Systematic Study of Compression Ordering for Lar…

Compressing large language models (LLMs), often consisting of billions of parameters, provides faster inference, smaller memory footprints, and enables local deployment. Two standard compression techniques are pruning and quantization, with…

Compression methods, including quantization, distillation, and pruning, improve the computational efficiency of large reasoning models (LRMs). However, existing studies either fail to sufficiently compare all three compression methods on…

Deep learning models have achieved tremendous success in most of the industries in recent years. The evolution of these models has also led to an increase in the model size and energy requirement, making it difficult to deploy in production…

Quantization, knowledge distillation, and magnitude pruning are among the most popular methods for neural network compression in NLP. Independently, these methods reduce model size and can accelerate inference, but their relative benefit…

Large Language Models (LLMs) have revolutionized many areas of artificial intelligence (AI), but their substantial resource requirements limit their deployment on mobile and edge devices. This survey paper provides a comprehensive overview…

Large Language Models (LLMs) enable advanced natural language processing but face deployment challenges on resource-constrained edge devices due to high computational, memory, and energy demands. Optimizing these models requires addressing…

Modern deployment often requires trading accuracy for efficiency under tight CPU and memory constraints, yet common compression proxies such as parameter count or FLOPs do not reliably predict wall-clock inference time. In particular,…

Model compression is increasingly essential for deploying large language models (LLMs), yet existing comparative studies largely focus on pruning and quantization evaluated primarily on knowledge-centric benchmarks. Thus, we introduce…

Language models have proven successful across a wide range of software engineering tasks, but their significant computational costs often hinder their practical adoption. To address this challenge, researchers have begun applying various…

Advancements in Natural Language Processing are heavily reliant on the Transformer architecture, whose improvements come at substantial resource costs due to ever-growing model sizes. This study explores optimization techniques, including…

Multimodal Large Language Models (MLLMs) hold huge potential for usage in the medical domain, but their computational costs necessitate efficient compression techniques. This paper evaluates the impact of structural pruning and…

Large Language Models (LLMs) have transformed natural language processing tasks successfully. Yet, their large size and high computational needs pose challenges for practical use, especially in resource-limited settings. Model compression…

What happens when multiple compression methods are combined-does the order in which they are applied matter? Joint model compression has emerged as a powerful strategy to achieve higher efficiency by combining multiple methods such as…

Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications, from search and recommendation systems to generative tasks. Although scaling laws indicate that larger models generally…

Large language models (LLMs) targeting different deployment scales and sizes are currently produced by training each variant from scratch; this is extremely compute-intensive. In this paper, we investigate if pruning an existing LLM and…

Structured pruning and knowledge distillation (KD) are typical techniques for compressing large language models, but it remains unclear how they should be applied at pretraining scale, especially to recent mixture-of-experts (MoE) models.…

Quantization and pruning form the foundation of compression for neural networks, enabling efficient inference for large language models (LLMs). Recently, various quantization and pruning techniques have demonstrated remarkable performance…

Compressing high-capability Large Language Models (LLMs) has emerged as a favored strategy for resource-efficient inferences. While state-of-the-art (SoTA) compression methods boast impressive advancements in preserving benign task…

This paper introduces LLM-Streamline, a pioneer work on layer pruning for large language models (LLMs). It is based on the observation that different layers have varying impacts on hidden states, enabling the identification of less…

Increasingly, model compression techniques enable large language models (LLMs) to be deployed in real-world applications. As a result of this momentum towards local deployment, compressed LLMs will interact with a large population. Prior…