English
Related papers

Related papers: PAT: Accelerating LLM Decoding via Prefix-Aware At…

200 papers

With reasoning becoming the generative paradigm for large language models (LLMs), the memory bottleneck caused by KV cache during the decoding phase has become a critical factor limiting high-concurrency service. Although existing KV cache…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-11 Mengqi Liao , Lu Wang , Chaoyun Zhang , Bo Qiao , Si Qin , Qingwei Lin , Saravan Rajmohan , Dongmei Zhang , Huaiyu Wan

Despite the significant success of large language models (LLMs), their extensive memory requirements pose challenges for deploying them in long-context token generation. The substantial memory footprint of LLM decoders arises from the…

Machine Learning · Computer Science 2024-02-12 Amir Zandieh , Insu Han , Vahab Mirrokni , Amin Karbasi

Large language models (LLMs) are increasingly deployed under the Model-as-a-Service (MaaS) paradigm. To meet stringent quality-of-service (QoS) requirements, existing LLM serving systems disaggregate the prefill and decode phases of…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-20 Ao Xu , Han Zhao , Weihao Cui , Quan Chen , Yukang Chen , Shulai Zhang , Shuang Chen , Jiemin Jiang , Zhibin Yu , Minyi Guo

Deploying Large Language Models (LLMs) on resource-constrained edge devices faces critical bottlenecks in memory bandwidth and power consumption. While ternary quantization (e.g., BitNet b1.58) significantly reduces model size, its direct…

Hardware Architecture · Computer Science 2026-05-05 Zi-Wei Lin , Tian-Sheuan Chang

Existing video coding for machines is often trained for a specific downstream task and model. As a result, the compressed representation becomes tightly coupled to the end task, making it difficult to scale across multiple tasks or adapt to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Wei Jiang , Wei Wang

LLMs are widely adopted in production, pushing inference systems to their limits. Disaggregated LLM serving (e.g., PD separation and KV state disaggregation) improves scalability and cost efficiency, but it also turns KV into an explicit…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-14 Zedong Liu , Xinyang Ma , Dejun Luo , Hairui Zhao , Bing Lu , Wenjing Huang , Yida Gu , Xingchen Liu , Zheng Wei , Jinyang Liu , Dingwen Tao , Guangming Tan

A long-standing goal in both industry and academia is to develop an LLM inference platform that is portable across hardware architectures, eliminates the need for low-level hand-tuning, and still delivers best-in-class efficiency. In this…

Machine Learning · Computer Science 2025-11-18 Burkhard Ringlein , Jan van Lunteren , Radu Stoica , Thomas Parnell

KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empirically. Existing systems rely on average-case robustness, with no mechanism to detect or…

Machine Learning · Computer Science 2026-05-21 Dean Calver

Large language model (LLM) serving is now limited by the key-value (KV) cache. During decode, each new token rereads prior KV state, so attention becomes a bandwidth- and capacity-heavy memory task. HBM-PIM helps by moving attention closer…

Hardware Architecture · Computer Science 2026-05-08 Zhuoran Li , Zhuohang Bian , Zihao Huang , Guangyu Sun , Yun Liang , Youwei Zhuo

Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first-token) and proceeding without it (reduced quality).…

Databases · Computer Science 2026-05-19 Rajveer Bachkaniwala , Chengqi Luo , Richard So , Divya Mahajan , Kexin Rong

Prefix KV caching has become a key mechanism in LLM serving: it reduces time to first token (TTFT) by avoiding redundant computation across requests that share a prefix (i.e., the system prompt). However, the accumulated KV cache is often…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-25 Yu Zhu , Aditya Dhakal , Yunming Xiao , Dejan Milojicic , Gustavo Alonso

The memory and computational demands of Key-Value (KV) cache present significant challenges for deploying long-context language models. Previous approaches attempt to mitigate this issue by selectively dropping tokens, which irreversibly…

Machine Learning · Computer Science 2024-07-24 Hanlin Tang , Yang Lin , Jing Lin , Qingsen Han , Shikuan Hong , Yiwu Yao , Gongyi Wang

Prefix caching is a key optimization in Large Language Model (LLM) serving, reusing attention Key-Value (KV) states across requests with shared prompt prefixes to reduce expensive prefill computation. However, its benefit depends critically…

Machine Learning · Computer Science 2026-05-20 Shaoke Fang , Ziang Li , Wenfei Wu , Jiatong Ji , Qingsong Liu , Ruizhi Pu

Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding but suffer from prohibitive quadratic computational complexity and memory overhead during inference. Current caching techniques accelerate…

Computation and Language · Computer Science 2025-11-06 Yuerong Song , Xiaoran Liu , Ruixiao Li , Zhigeng Liu , Zengfeng Huang , Qipeng Guo , Ziwei He , Xipeng Qiu

Large language models (LLMs) represent a groundbreaking advancement in the domain of natural language processing due to their impressive reasoning abilities. Recently, there has been considerable interest in increasing the context lengths…

Machine Learning · Computer Science 2024-11-11 Utkarsh Saxena , Gobinda Saha , Sakshi Choudhary , Kaushik Roy

Large language models (LLMs) have achieved remarkable success in natural language tasks, but their inference incurs substantial computational and memory overhead. To improve efficiency, parallel decoding methods like Skeleton-of-Thought…

Computation and Language · Computer Science 2025-04-15 Shuowei Jin , Xueshen Liu , Yongji Wu , Haizhong Zheng , Qingzhao Zhang , Atul Prakash , Matthew Lentz , Danyang Zhuo , Feng Qian , Z. Morley Mao

Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts…

Computation and Language · Computer Science 2024-06-04 Jungmin Yun , Mihyeon Kim , Youngbin Kim

Pre-trained language models (PLM) have demonstrated their effectiveness for a broad range of information retrieval and natural language processing tasks. As the core part of PLM, multi-head self-attention is appealing for its ability to…

Computation and Language · Computer Science 2022-04-07 Shanshan Wang , Zhumin Chen , Zhaochun Ren , Huasheng Liang , Qiang Yan , Pengjie Ren

Serving long-context LLMs is costly because attention computation grows linearly with context length. Dynamic sparse attention algorithms (DSAs) mitigate this by attending only to the key-value (KV) cache of critical tokens. However, with…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Qihui Zhou , Peiqi Yin , Pengfei Zuo , James Cheng

Rapid advances in Large Language Models (LLMs) have spurred demand for processing extended context sequences in contemporary applications. However, this progress faces two challenges: performance degradation due to sequence lengths…

Computation and Language · Computer Science 2025-10-10 Wei Wu , Zhuoshi Pan , Chao Wang , Liyi Chen , Yunchu Bai , Tianfu Wang , Kun Fu , Zheng Wang , Hui Xiong