English
Related papers

Related papers: SPA-Cache: Singular Proxies for Adaptive Caching i…

200 papers

Autoregressive large language models achieve strong results on many benchmarks, but decoding remains fundamentally latency-limited by sequential dependence on previously generated tokens. Diffusion language models (DLMs) promise parallel…

Computation and Language · Computer Science 2026-01-06 Yihao Liang , Ze Wang , Hao Chen , Ximeng Sun , Jialian Wu , Xiaodong Yu , Jiang Liu , Emad Barsoum , Zicheng Liu , Niraj K. Jha

Large Language Models (LLMs) are increasingly deployed in large-scale online services, enabling sophisticated applications. However, the computational overhead of generating key-value (KV) caches in the prefill stage presents a major…

Machine Learning · Computer Science 2025-02-24 Shuowei Jin , Xueshen Liu , Qingzhao Zhang , Z. Morley Mao

The transformer's context window is vital for tasks such as few-shot learning and conditional generation as it preserves previous tokens for active memory. However, as the context lengths increase, the computational costs grow…

Computation and Language · Computer Science 2025-04-01 Jeffrey Willette , Heejun Lee , Youngwan Lee , Myeongjae Jeon , Sung Ju Hwang

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

Linear sequence modeling approaches, such as linear attention, provide advantages like linear-time training and constant-memory inference over sequence lengths. However, existing sequence parallelism (SP) methods are either not optimized…

Machine Learning · Computer Science 2025-02-12 Weigao Sun , Disen Lan , Yiran Zhong , Xiaoye Qu , Yu Cheng

As Large Language Models (LLMs) can now process extremely long contexts, efficient inference over these extended inputs has become increasingly important, especially for emerging applications like LLM agents that highly depend on this…

Computation and Language · Computer Science 2026-04-09 Penghui Yang , Cunxiao Du , Fengzhuo Zhang , Haonan Wang , Tianyu Pang , Chao Du , Bo An

The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing KV cache compression methods alleviate memory pressure, they…

Computation and Language · Computer Science 2026-05-06 Jinyu Guo , Zhihan Zhang , Jiehui Xie , Md. Tamim Iqbal , Dongshen Han , Lik-Hang Lee , Sung-Ho Bae , Jie Zou , Yang Yang , Chaoning Zhang

Deployment of autoregressive large language models (LLMs) is costly, and as these models increase in size, the associated costs will become even more considerable. Consequently, different methods have been proposed to accelerate the token…

Computation and Language · Computer Science 2024-07-03 Parsa Kavehzadeh , Mohammadreza Pourreza , Mojtaba Valipour , Tinashu Zhu , Haoli Bai , Ali Ghodsi , Boxing Chen , Mehdi Rezagholizadeh

Large Language Models have excelled in various domains but face efficiency challenges due to the growing Key-Value (KV) cache required for long-sequence inference. Recent efforts aim to reduce KV cache size by evicting vast non-critical…

Computation and Language · Computer Science 2025-10-17 Yuan Feng , Junlin Lv , Yukun Cao , Xike Xie , S. Kevin Zhou

Speculative decoding (SD) has been demonstrated as an effective technique for lossless LLM inference acceleration. Retrieval-based SD methods, one kind of model-free method, have yielded promising speedup, but they often rely on incomplete…

Computation and Language · Computer Science 2024-12-17 Yuxuan Hu , Ke Wang , Xiaokang Zhang , Fanjin Zhang , Cuiping Li , Hong Chen , Jing Zhang

Current self-correction approaches in text-to-SQL face two critical limitations: 1) Conventional self-correction methods rely on recursive self-calls of LLMs, resulting in multiplicative computational overhead, and 2) LLMs struggle to…

Computation and Language · Computer Science 2025-06-03 Ge Qu , Jinyang Li , Bowen Qin , Xiaolong Li , Nan Huo , Chenhao Ma , Reynold Cheng

Large language models (LLMs) are commonly adapted to downstream tasks through fine-tuning, but fine-tuning data often contains sensitive information that may be leaked by the resulting model. Differential privacy (DP) offers formal…

Machine Learning · Computer Science 2026-05-19 Haichao Sha , Zihao Wang , Yuncheng Wu , Hong Chen , Wei Dong

Unlike autoregressive language models, which terminate variable-length generation upon predicting an End-of-Sequence (EoS) token, Diffusion Language Models (DLMs) operate over a fixed maximum-length context window for a predetermined number…

Computation and Language · Computer Science 2026-03-09 Vittorio Rossi , Giacomo Cirò , Davide Beltrame , Luca Gandolfi , Paul Röttger , Dirk Hovy

The increasing adoption of large language models (LLMs) necessitates inference serving systems that can deliver both high throughput and low latency. Deploying LLMs with hundreds of billions of parameters on memory-constrained GPUs exposes…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-10 Bowen Pang , Kai Li , Feifan Wang

The Key-Value (KV) cache is integral to efficient autoregressive inference in large language models (LLMs), yet its unbounded growth in stateful multi-turn scenarios presents major challenges. This paper examines the interplay between KV…

Machine Learning · Computer Science 2025-11-10 Pratik Poudel

The rapid adoption of large language models (LLMs) is pushing AI accelerators toward increasingly powerful and specialized designs. Instead of further complicating software development with deeply hierarchical scratchpad memories (SPMs) and…

Hardware Architecture · Computer Science 2025-12-09 Zhongchun Zhou , Chengtao Lai , Yuhang Gu , Wei Zhang

Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…

Artificial Intelligence · Computer Science 2025-05-27 Ahmet Caner Yüzügüler , Jiawei Zhuang , Lukas Cavigelli

Video diffusion models (VDMs) perform attention computation over the 3D spatio-temporal domain. Compared to large language models (LLMs) processing 1D sequences, their memory consumption scales cubically, necessitating parallel serving…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-09 Zhiyuan Wu , Shuai Wang , Li Chen , Kaihui Gao , Dan Li , Yanyu Ren , Qiming Zhang , Yong Wang

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

Computation and Language · Computer Science 2024-10-31 Suyu Ge , Yunan Zhang , Liyuan Liu , Minjia Zhang , Jiawei Han , Jianfeng Gao

Large Language Models (LLMs) are typically static after training, yet real-world applications require continual adaptation to new knowledge without degrading existing capabilities. Standard approaches to updating models, like full…

Machine Learning · Computer Science 2026-04-08 Satyam Goyal , Anirudh Kanchi , Garv Shah , Prakhar Gupta