English
Related papers

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

200 papers

High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV cache) memory for each request is huge and grows and shrinks…

Machine Learning · Computer Science 2023-09-13 Woosuk Kwon , Zhuohan Li , Siyuan Zhuang , Ying Sheng , Lianmin Zheng , Cody Hao Yu , Joseph E. Gonzalez , Hao Zhang , Ion Stoica

KV cache has traditionally been stored in GPU memory to accelerate the decoding phase of large language model (LLM) inference. However, it is increasingly necessary to move KV caches outside GPU devices, to enable cache reuse across…

Machine Learning · Computer Science 2025-12-08 Yuhan Liu , Yihua Cheng , Jiayi Yao , Yuwei An , Xiaokun Chen , Shaoting Feng , Yuyang Huang , Samuel Shen , Rui Zhang , Kuntai Du , Junchen Jiang

Diffusion-based large language models (dLLMs) have recently gained significant attention for their exceptional performance and inherent potential for parallel decoding. Existing frameworks further enhance its inference efficiency by…

Computation and Language · Computer Science 2025-12-01 Linye Wei , Wenjue Chen , Pingzhi Tang , Xiaotian Guo , Le Ye , Runsheng Wang , Meng Li

Deploying Large Language Models (LLMs) on edge devices remains challenging due to their quadratically increasing computations with the sequence length. Existing studies for dynamic attention pruning are designed for hardware with massively…

Artificial Intelligence · Computer Science 2025-07-29 Jiawen Qi , Chang Gao , Zhaochun Ren , Qinyu Chen

Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. This surge in demand poses significant challenges in optimizing throughput and latency while keeping costs manageable. The Key-Value…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-07-23 Jiale Xu , Rui Zhang , Cong Guo , Weiming Hu , Zihan Liu , Feiyang Wu , Yu Feng , Shixuan Sun , Changxu Shao , Yuhong Guo , Junping Zhao , Ke Zhang , Minyi Guo , Jingwen Leng

The increasing size of the Key-Value (KV) cache during the Large Language Models long-context inference is the main obstacle for its balance between the deployment cost and task accuracy. To reduce the KV cache size in such scenarios, most…

Machine Learning · Computer Science 2025-07-25 Manlai Liang , JiaMing Zhang , Xiong Li , Jinlong Li

Large Language Models (LLMs) are increasingly deployed in scenarios demanding ultra-long context reasoning, such as agentic workflows and deep research understanding. However, long-context inference is constrained by the KV cache, a…

Hardware Architecture · Computer Science 2026-03-11 Jianlong Lei , Shashikant Ilager

The increasing memory demand of the Key-Value (KV) cache poses a significant bottleneck for Large Language Models (LLMs) in long-context applications. Existing low-rank KV compression methods reduce this footprint by modifying model…

Computation and Language · Computer Science 2026-05-14 Shiyu Ji , Yixuan Wang , Yijun Liu , Qingfu Zhu , Wanxiang Che

Auto-regressive Large Language Models (LLMs) demonstrate remarkable performance across different domains such as vision and language processing. However, due to sequential processing through a stack of transformer layers, autoregressive…

Computation and Language · Computer Science 2025-08-28 Akriti Jain , Saransh Sharma , Koyel Mukherjee , Soumyabrata Pal

The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed KV vectors. However, its memory consumption scales linearly…

Machine Learning · Computer Science 2024-10-07 Rongzhi Zhang , Kuang Wang , Liyuan Liu , Shuohang Wang , Hao Cheng , Chao Zhang , Yelong Shen

KV caching significantly improves the efficiency of Large Language Model (LLM) inference by storing attention states from previously processed tokens, enabling faster generation of subsequent tokens. However, as sequence length increases,…

Both performance and efficiency are crucial factors for sequence labeling tasks in many real-world scenarios. Although the pre-trained models (PTMs) have significantly improved the performance of various sequence labeling tasks, their…

Computation and Language · Computer Science 2021-06-15 Xiaonan Li , Yunfan Shao , Tianxiang Sun , Hang Yan , Xipeng Qiu , Xuanjing Huang

The demand for efficient large language model (LLM) inference has propelled the development of dedicated accelerators. As accelerators are vulnerable to hardware faults due to aging, variation, etc, existing accelerator designs often…

Hardware Architecture · Computer Science 2025-04-08 Tong Xie , Jiawang Zhao , Zishen Wan , Zuodong Zhang , Yuan Wang , Runsheng Wang , Ru Huang , Meng Li

Autoregressive decoding in large language models (LLMs) requires caching a growing list of past key-value (KV) pairs, making long-context inference a memory-bound problem. While recent methods have explored quantizing the cache, evicting…

Computation and Language · Computer Science 2025-10-08 Harshil Vejendla

Reinforcement learning (RL) for large language models (LLMs) is increasingly bottlenecked by rollout (generation), where long output sequence lengths make attention and KV-cache memory dominate end-to-end step time. FP8 offers an attractive…

Machine Learning · Computer Science 2026-04-13 Zhaopeng Qiu , Shuang Yu , Jingqi Zhang , Shuai Zhang , Xue Huang , Jingyi Yang , Junjie Lai

Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-29 Mingyu Sun , Xiao Zhang , Shen Qu , Yan Li , Mengbai Xiao , Yuan Yuan , Dongxiao Yu

We present a novel inference scheme, self-speculative decoding, for accelerating Large Language Models (LLMs) without the need for an auxiliary model. This approach is characterized by a two-stage process: drafting and verification. The…

Computation and Language · Computer Science 2025-02-11 Jun Zhang , Jue Wang , Huan Li , Lidan Shou , Ke Chen , Gang Chen , Sharad Mehrotra

Large Language Model (LLM) inference requires substantial computational resources, yet CPU-based inference remains essential for democratizing AI due to the widespread availability of CPUs compared to specialized accelerators. However,…

Hardware Architecture · Computer Science 2025-10-01 Jingyao Zhang , Jaewoo Park , Jongeun Lee , Elaheh Sadredini

Large reasoning models achieve strong performance on complex tasks by generating extended chains of thought, but they often "overthink": continuing to reason long after they have enough information to answer correctly. This wastes…

Computation and Language · Computer Science 2025-12-08 Ömer Faruk Akgül , Yusuf Hakan Kalaycı , Rajgopal Kannan , Willie Neiswanger , Viktor Prasanna

The efficiency of large vision-language models (LVLMs) is constrained by the computational bottleneck of the attention mechanism during the prefill phase and the memory bottleneck of fetching the key-value (KV) cache in the decoding phase,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Yefei He , Feng Chen , Jing Liu , Wenqi Shao , Hong Zhou , Kaipeng Zhang , Bohan Zhuang