中文
相关论文

相关论文: Prune&Comp: Free Lunch for Layer-Pruned LLMs via I…

200 篇论文

Large Language Models (LLMs) exhibit strong reasoning abilities, but their high computational costs limit their practical deployment. Recent studies reveal significant redundancy in LLMs layers, making layer pruning an active research…

计算与语言 · 计算机科学 2026-02-17 Hao Liu , Guangyan Li , Wensheng Zhang , Yongqiang Tang

Although large language models (LLMs) have achieved revolutionary breakthroughs in many fields, their large model size and high computational cost pose significant challenges for practical deployment on resource-constrained edge devices. To…

机器学习 · 计算机科学 2025-10-29 Yao Lu , Yuqi Li , Wenbin Xie , Shanqing Yu , Qi Xuan , Zhaowei Zhu , Shiping Wen

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…

机器学习 · 计算机科学 2024-11-26 Yao Lu , Hao Cheng , Yujie Fang , Zeyu Wang , Jiaheng Wei , Dongwei Xu , Qi Xuan , Xiaoniu Yang , Zhaowei Zhu

Pruning has recently been widely adopted to reduce the parameter scale and improve the inference efficiency of Large Language Models (LLMs). Mainstream pruning techniques often rely on uniform layerwise pruning strategies, which can lead to…

计算与语言 · 计算机科学 2025-06-04 Yuli Chen , Bo Cheng , Jiale Han , Yingying Zhang , Yingting Li , Shuhao Zhang

We introduce Probe Pruning (PP), a novel framework for online, dynamic, structured pruning of Large Language Models (LLMs) applied in a batch-wise manner. PP leverages the insight that not all samples and tokens contribute equally to the…

计算与语言 · 计算机科学 2025-02-24 Qi Le , Enmao Diao , Ziyan Wang , Xinran Wang , Jie Ding , Li Yang , Ali Anwar

Layer pruning has emerged as a widely used technique for compressing large language models (LLMs). However, existing layer pruning approaches often incur substantial performance degradation. We identify the majority of this degradation to a…

计算与语言 · 计算机科学 2025-10-28 Xinrui Chen , Haoli Bai , Tao Yuan , Ruikang Liu , Kang Zhao , Xianzhi Yu , Lu Hou , Tian Guan , Yonghong He , Chun Yuan

The high computational demands of Large Language Models (LLMs) motivate methods that reduce parameter count and accelerate inference. In response, model pruning emerges as an effective strategy, yet current methods typically focus on a…

Structured pruning of modern large language models (LLMs) has emerged as a way of decreasing their high computational needs. Width pruning reduces the size of projection weight matrices (e.g., by removing attention heads) while maintaining…

机器学习 · 计算机科学 2024-06-25 Bo-Kyeong Kim , Geonmin Kim , Tae-Ho Kim , Thibault Castells , Shinkook Choi , Junho Shin , Hyoung-Kyu Song

Considering the hardware-friendly characteristics and broad applicability, structured pruning has emerged as an efficient solution to reduce the resource demands of large language models (LLMs) on resource-constrained devices. Traditional…

机器学习 · 计算机科学 2025-01-28 Zihuai Xu , Yang Xu , Hongli Xu , Yunming Liao , Zhiwei Yao , Zuan Xie

Small language models (SLMs) have attracted considerable attention from both academia and industry due to their broad range of applications in edge devices. To obtain SLMs with strong performance, conventional approaches either pre-train…

机器学习 · 计算机科学 2025-11-17 Rui Pan , Shivanshu Shekhar , Boyao Wang , Shizhe Diao , Jipeng Zhang , Xingyuan Pan , Renjie Pi , Tong Zhang

Layer pruning efficiently reduces Large Language Model (LLM) computational costs but often triggers sudden performance collapse. Existing representation-based analyses struggle to explain this mechanism. We propose studying pruning through…

计算与语言 · 计算机科学 2026-05-11 Boyu Shi , Chang Liu , ChuanBao Gao , Xu Yang , Xin Geng

Despite exceptional capabilities, Large Language Models (LLMs) still face deployment challenges due to their enormous size. Post-training structured pruning is a promising solution that prunes LLMs without the need for retraining, reducing…

机器学习 · 计算机科学 2025-02-21 Weizhong Huang , Yuxin Zhang , Xiawu Zheng , Fei Chao , Rongrong Ji

Despite the remarkable success of Large Language Models (LLMs), the massive size poses significant deployment challenges, particularly on resource-constrained hardware. While existing LLM compression methods focus on quantization, pruning…

人工智能 · 计算机科学 2023-10-12 Song Guo , Jiahang Xu , Li Lyna Zhang , Mao Yang

Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. However, such impressive capability typically comes with a substantial model size, which presents significant challenges in deployment…

计算与语言 · 计算机科学 2025-06-26 Guinan Su , Li Shen , Lu Yin , Shiwei Liu , Yanwu Yang , Jonas Geiping

N:M structured pruning is essential for large language models (LLMs) because it can remove less important network weights and reduce the memory and computation requirements. Existing pruning methods mainly focus on designing metrics to…

计算与语言 · 计算机科学 2025-03-17 Chi Xu , Gefei Zhang , Yantong Zhu , Luca Benini , Guosheng Hu , Yawei Li , Zhihong Zhang

Large language models (LLMs) enable unparalleled few- and zero-shot reasoning capabilities but at a high computational footprint. A growing assortment of methods for compression promises to reduce the computational burden of LLMs in…

计算与语言 · 计算机科学 2024-07-11 Ananya Harsh Jha , Tom Sherborne , Evan Pete Walsh , Dirk Groeneveld , Emma Strubell , Iz Beltagy

Large language models (LLMs) based on transformer are witnessing a notable trend of size expansion, which brings considerable costs to both model training and inference. However, existing methods such as model quantization, knowledge…

计算与语言 · 计算机科学 2024-10-16 Yifei Yang , Zouying Cao , Hai Zhao

Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency. However, conventional training-free structured pruning methods often employ a heuristic metric that…

计算与语言 · 计算机科学 2026-01-28 Songtao Liu , Peng Liu

In this paper, we propose a rotation-constrained compensation method to address the errors introduced by structured pruning of large language models (LLMs). LLMs are trained on massive datasets and accumulate rich semantic knowledge in…

计算与语言 · 计算机科学 2026-03-02 Shuichiro Haruta , Kazunori Matsumoto , Zhi Li , Yanan Wang , Mori Kurokawa

As Large Language Models (LLMs) grow dramatically in size, there is an increasing trend in compressing and speeding up these models. Previous studies have highlighted the usefulness of gradients for importance scoring in neural network…

计算与语言 · 计算机科学 2024-07-17 Hongrong Cheng , Miao Zhang , Javen Qinfeng Shi
‹ 上一页 1 2 3 10 下一页 ›