Related papers: Greedy Output Approximation: Towards Efficient Str…

Although large language models (LLMs) have achieved remarkable success across various domains, their considerable scale necessitates substantial computational resources, posing significant challenges for deployment in resource-constrained…

This paper presents an efficient technique to prune deep and/or wide convolutional neural network models by eliminating redundant features (or filters). Previous studies have shown that over-sized deep neural network models tend to produce…

Fine-tuning transformer models after unsupervised pre-training reaches a very high performance on many different natural language processing tasks. Unfortunately, transformers suffer from long inference times which greatly increases costs…

Leveraging Large Language Models (LLMs) for recommendation has recently garnered considerable attention, where fine-tuning plays a key role in LLMs' adaptation. However, the cost of fine-tuning LLMs on rapidly expanding recommendation data…

Non-uniform structured network pruning methods can effectively reduce Large Language Model (LLM) size by eliminating redundant channels or layers, offering lower performance degradation than uniform strategies. However, existing non-uniform…

Depth pruning improves the inference efficiency of large language models by removing Transformer blocks. Prior work typically treats layer redundancy as an inherent structural property of pretrained networks, emphasizing importance criteria…

Structured pruning of large language models (LLMs) offers substantial efficiency improvements by removing entire hidden units, yet current approaches often suffer from significant performance degradation, particularly in zero-shot settings,…

Depth pruning aims to reduce the inference cost of a large language model without any hardware-specific complications, by simply removing several less important transformer blocks. However, our empirical findings suggest that the importance…

In recent years, the size of pre-trained language models (PLMs) has grown by leaps and bounds. However, efficiency issues of these large-scale PLMs limit their utilization in real-world scenarios. We present a suite of cost-effective…

As their size increases, Large Languages Models (LLMs) are natural candidates for network pruning methods: approaches that drop a subset of network weights while striving to preserve performance. Existing methods, however, require either…

The rapid development in the performance of large language models (LLMs) is accompanied by the escalation of model size, leading to the increasing cost of model training and inference. Previous research has discovered that certain layers in…

Large Language Models (LLMs) have become indispensable across various domains, but this comes at the cost of substantial computational and memory resources. Model pruning addresses this by removing redundant components from models. In…

Making large language models (LLMs) more efficient in memory, latency, and serving cost is crucial for edge deployment, interactive applications, and sustainable inference at scale. Pruning is a promising technique, but existing pruning…

Large language models (LLMs) often develop learned mechanisms specialized to specific datasets, such as reliance on domain-specific correlations, which yield high-confidence predictions without generalizable reasoning. While beneficial in…

In AI research, the optimization of Large Language Models (LLMs) remains a significant challenge, crucial for advancing the field's practical applications and sustainability. Building upon the foundational work of Professor Song Han's lab…

The resource requirements of neural networks can be significantly reduced through pruning - the removal of seemingly less important parameters. However, for LLMs, full retraining to recover pruning-induced performance degradation is often…

Large volumes of text data have contributed significantly to the development of large language models (LLMs) in recent years. This data is typically acquired by scraping the internet, leading to pretraining datasets comprised of noisy web…

Most existing structured pruning methods for Large Language Models (LLMs) require substantial computational and data resources for retraining to reestablish the corrupted correlations, making them prohibitively expensive. To address this,…

As Large Language Models (LLMs) continue to advance in performance, their size has escalated significantly, with current LLMs containing billions or even trillions of parameters. However, in this study, we discovered that many layers of…

Large Vision-Language Models (LVLMs) rely on dense visual tokens to capture fine-grained visual information, but processing all these tokens incurs substantial computational and memory overhead during inference. To address this issue, we…