相关论文: Sample-aware Adaptive Structured Pruning for Large…

Large language models (LLMs) face significant deployment challenges due to their massive computational demands. % While pruning offers a promising compression solution, existing methods suffer from two critical limitations: (1) They neglect…

Many efforts have been made to facilitate natural language processing tasks with pre-trained language models (LMs), and brought significant improvements to various applications. To fully leverage the nearly unlimited corpora and capture…

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…

Large language models (LLMs) are expensive to serve because model parameters, attention computation, and KV caches impose substantial memory and latency costs. We present GRASPrune, a structured pruning framework applied after pretraining…

Latent Diffusion Models (LDMs) have emerged as powerful generative models, known for delivering remarkable results under constrained computational resources. However, deploying LDMs on resource-limited devices remains a complex issue,…

Auto-regressive large language models such as GPT-3 require enormous computational resources to use. Traditionally, structured pruning methods are employed to reduce resource usage. However, their application to and efficacy for generative…

The rapid increase in the parameter counts of Large Language Models (LLMs), which often reach into the billions or even trillions, presents significant challenges for their practical deployment, particularly in resource-constrained…

Visual token reduction is critical for accelerating Vision-Language Models (VLMs), yet most existing approaches rely on a fixed budget shared across all inputs, overlooking the substantial variation in image information density. We propose…

Model pruning technique is vital for accelerating large language models by reducing their size and computational requirements. However, the generalizability of existing pruning methods across diverse datasets and tasks remains unclear.…

Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their increasing parameter sizes significantly slow down inference. Speculative decoding mitigates this issue by leveraging a smaller draft…

We propose a novel Two-Stage framework for Structured Pruning (\textsc{2SSP}) for pruning Large Language Models (LLMs), which combines two different strategies of pruning, namely Width and Depth Pruning. The first stage (Width Pruning)…

Large Language Models (LLMs) are not only resource-intensive to train but even more costly to deploy in production. Therefore, recent work has attempted to prune blocks of LLMs based on cheap proxies for estimating block importance,…

Large Language Models (LLMs) have experienced significant growth and development in recent years. However, performing inference on LLMs remains costly, especially for long-context inference or in resource-constrained devices. This motivates…

In multimodal large language models (MLLMs), the length of input visual tokens is often significantly greater than that of their textual counterparts, leading to a high inference cost. Many works aim to address this issue by removing…

Large Language Models (LLMs) are widely deployed in real-world applications, yet their internal mechanisms remain difficult to interpret and control, limiting our ability to diagnose and correct undesirable behaviors. Mechanistic…

Recent advances in vision-language models (VLMs) have shown remarkable performance across multimodal tasks, yet their ever-growing scale poses severe challenges for deployment and efficiency. Existing compression methods often rely on…

The rapid proliferation of large language models (LLMs) in natural language processing (NLP) has created a critical need for techniques that enable efficient deployment on memory-constrained devices without compromising performance. We…

Due to the large number of parameters, the inference phase of Large Language Models (LLMs) is resource-intensive. However, not all requests posed to LLMs are equally difficult to handle. Through analysis, we show that for some tasks, LLMs…

In this article, we explore the challenges and evolution of two key technologies in the current field of AI: Vision Transformer model and Large Language Model (LLM). Vision Transformer captures global information by splitting images into…

Recent work targeting large language models (LLMs) for code generation demonstrated that increasing the amount of training data through synthetic code generation often leads to exceptional performance. In this paper we explore data pruning…