English
Related papers

Related papers: River-LLM: Large Language Model Seamless Exit Base…

200 papers

Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the…

Computation and Language · Computer Science 2024-06-05 Haoyi Wu , Kewei Tu

Large Language Models (LLMs) have revolutionized AI applications, but deploying them at scale presents significant challenges. We present RTP-LLM, a high-performance inference engine for industrial-scale LLM deployment, successfully…

Increasing the size of large language models (LLMs) has been shown to lead to better performance. However, this comes at the cost of slower and more expensive inference. Early-exiting is a promising approach for improving the efficiency of…

Computation and Language · Computer Science 2024-10-31 Jort Vincenti , Karim Abdel Sadek , Joan Velja , Matteo Nulli , Metod Jazbec

Large Language Model (LLM) inference uses an autoregressive manner to generate one token at a time, which exhibits notably lower operational intensity compared to earlier Machine Learning (ML) models such as encoder-only transformers and…

Hardware Architecture · Computer Science 2025-05-06 Yufeng Gu , Alireza Khadem , Sumanth Umesh , Ning Liang , Xavier Servot , Onur Mutlu , Ravi Iyer , Reetuparna Das

In this paper, we propose Patience-based Early Exit, a straightforward yet effective inference method that can be used as a plug-and-play technique to simultaneously improve the efficiency and robustness of a pretrained language model…

Computation and Language · Computer Science 2020-10-23 Wangchunshu Zhou , Canwen Xu , Tao Ge , Julian McAuley , Ke Xu , Furu Wei

Retrieval-Augmented Language Modeling (RALM) by integrating large language models (LLM) with relevant documents from an external corpus is a proven method for enabling the LLM to generate information beyond the scope of its pre-training…

Computation and Language · Computer Science 2025-06-16 Runheng Liu , Xingchen Xiao , Heyan Huang , Zewen Chi , Zhijing Wu

Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV states to account for…

Machine Learning · Computer Science 2026-04-20 Chuangtao Chen , Grace Li Zhang , Xunzhao Yin , Cheng Zhuo , Bing Li , Ulf Schlichtmann

Large language models (LLMs) excel across diverse tasks but face significant deployment challenges due to high inference costs. LLM inference comprises prefill (compute-bound) and decode (memory-bound) stages, with decode dominating latency…

Artificial Intelligence · Computer Science 2025-08-13 Woojeong Kim , Junxiong Wang , Jing Nathan Yan , Mohamed Abdelfattah , Alexander M. Rush

Transformer-based pre-trained language models (PLMs) mostly suffer from excessive overhead despite their advanced capacity. For resource-constrained devices, there is an urgent need for a spatially and temporally efficient model which…

Computation and Language · Computer Science 2022-10-28 Bowen Shen , Zheng Lin , Yuanxin Liu , Zhengxiao Liu , Lei Wang , Weiping Wang

Withtherapid advancement of large language models (LLMs), the context length for inference has been continuously increasing, leading to an exponential growth in the demand for Key-Value (KV) caching. This has resulted in a significant…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-11 Yanyu Liu , Jingying Fu , Sixiang Liu , Yitian Zou , You Fu , Jiehan Zhou , Shouhua Zhang

Diffusion-based large language models (dLLMs) rely on bidirectional attention, which prevents lossless KV caching and requires a full forward pass at every denoising step. Existing approximate KV caching methods reduce this cost by…

Computation and Language · Computer Science 2026-03-20 Minsoo Cheong , Donghyun Son , Woosang Lim , Sungjoo Yoo

Autoregressive large language models (LLMs) are bottlenecked by sequential decoding, where each new token typically requires executing all transformer layers. Existing dynamic-depth and layer-skipping methods reduce this cost, but often…

Computation and Language · Computer Science 2026-01-07 Hossein Rajabzadeh , Maryam Dialameh , Chul B. Park , Il-Min Kim , Hyock Ju Kwon

Recent advancements in Large Language Models (LLMs) have spurred interest in numerous applications requiring robust long-range capabilities, essential for processing extensive input contexts and continuously generating extended outputs. As…

Machine Learning · Computer Science 2025-07-22 Dachuan Shi , Yonggan Fu , Xiangchi Yuan , Zhongzhi Yu , Haoran You , Sixu Li , Xin Dong , Jan Kautz , Pavlo Molchanov , Yingyan , Lin

In recent years, Vision-Language Models (VLMs) have shown remarkable performance improvements in Vision-Language tasks. However, their large size poses challenges for real-world applications where inference latency is a concern. To tackle…

Machine Learning · Computer Science 2025-06-10 Divya Jyoti Bajpai , Manjesh Kumar Hanawal

Early-Exit (EE) is a Large Language Model (LLM) architecture that accelerates inference by allowing easier tokens to be generated using only a subset of the model's layers. However, traditional batching frameworks are ill-suited for EE…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-18 Xuting Liu , Daniel Alexander , Siva Kesava Reddy Kakarla , Behnaz Arzani , Vincent Liu

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction. However, practical dLLM decoding still suffers from high inference latency, which limits…

Computation and Language · Computer Science 2026-04-22 Zhenbang Du , Kejing Xia , Xinrui Zhong , Yonggan Fu , Nicolai Oswald , Binfei Ji , Brucek Khailany , Pavlo Molchanov , Yingyan Lin

How to efficiently serve Large Language Models (LLMs) has become a pressing issue because of their huge computational cost in their autoregressive generation process. To mitigate computational costs, LLMs often employ the KV Cache technique…

Computation and Language · Computer Science 2024-07-23 Zheng Wang , Boxiao Jin , Zhongzhi Yu , Minjia Zhang

Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI. Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value (KV) cache during…

Computation and Language · Computer Science 2025-07-16 Luohe Shi , Zuchao Li , Lefei Zhang , Guoming Liu , Baoyuan Qi , Hai Zhao

Scaling the input context length of a large language model (LLM) incurs a significant increase in computation cost and memory footprint to maintain the attention key-value (KV) cache. Existing KV cache compression methods suffer from…

Computation and Language · Computer Science 2025-01-31 Yuxiang Huang , Binhang Yuan , Xu Han , Chaojun Xiao , Zhiyuan Liu

Long-context reasoning is a critical capability of large language models (LLMs), enabling applications such as long-document understanding, summarization, and code generation. However, efficient autoregressive inference relies on the…

Computation and Language · Computer Science 2026-04-28 Zahra Dehghanighobadi , Asja Fischer