English
Related papers

Related papers: PRISM: Fast Online LLM Serving via Scheduling-Memo…

200 papers

KV cache restoration has emerged as a dominant bottleneck in serving long-context LLM workloads, including multi-turn conversations, retrieval-augmented generation, and agentic pipelines. Existing approaches treat restoration as a…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-29 Sean Nian , Jiahao Fang , Qilong Feng , Zhiyu Wu , Fan Lai

The key-value (KV) cache is a foundational optimization in Transformer-based large language models (LLMs), eliminating redundant recomputation of past token representations during autoregressive generation. However, its memory footprint…

Machine Learning · Computer Science 2026-03-24 Yichun Xu , Navjot K. Khaira , Tejinder Singh

Multi-agent Large Language Model (LLM) systems face a critical bottleneck: redundant transmission of contextual information between agents consumes excessive bandwidth and computational resources. Traditional approaches discard internal…

Computation and Language · Computer Science 2025-12-23 Boris Kriuk , Logic Ng

The revolutionary capabilities of Large Language Models (LLMs) are attracting rapidly growing popularity and leading to soaring user requests to inference serving systems. Caching techniques, which leverage data reuse to reduce computation,…

Computation and Language · Computer Science 2025-07-15 Longwei Zou , Yan Liu , Jiamu Kang , Tingfeng Liu , Jiangang Kong , Yangdong Deng

Retrieval-Augmented Generation (RAG) enhances the factuality of Large Language Models (LLMs) by incorporating retrieved documents and/or generated context. However, LLMs often exhibit a stylistic bias when presented with mixed contexts,…

Computation and Language · Computer Science 2026-04-21 Jiaang Li , Zhendong Mao , Quan Wang , Yuning Wan , Yongdong Zhang

Large Language Models are increasingly being deployed in datacenters. Serving these models requires careful memory management, as their memory usage includes static weights, dynamic activations, and key-value caches. While static weights…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-08 Jiale Xu , Rui Zhang , Yi Xiong , Cong Guo , Zihan Liu , Yangjie Zhou , Weiming Hu , Hao Wu , Changxu Shao , Ziqing Wang , Yongjie Yuan , Junping Zhao , Minyi Guo , Jingwen Leng

While large language models (LLMs) have made notable advancements in natural language processing, they continue to struggle with processing extensive text. Memory mechanism offers a flexible solution for managing long contexts, utilizing…

Computation and Language · Computer Science 2024-09-27 Bo Wang , Heyan Huang , Yixin Cao , Jiahao Ying , Wei Tang , Chong Feng

Current Retrieval-Augmented Generation (RAG) systems concatenate and process numerous retrieved document chunks for prefill which requires a large volume of computation, therefore leading to significant latency in time-to-first-token…

Computer Vision and Pattern Recognition · Computer Science 2024-10-11 Songshuo Lu , Hua Wang , Yutian Rong , Zhi Chen , Yaohua Tang

While traditional optimization and scheduling schemes are designed to meet fixed, predefined system requirements, future systems are moving toward user-driven approaches and personalized services, aiming to achieve high…

Computation and Language · Computer Science 2024-11-15 Thomas Mongaillard , Samson Lasaulce , Othman Hicheur , Chao Zhang , Lina Bariah , Vineeth S. Varma , Hang Zou , Qiyang Zhao , Merouane Debbah

Key-Value cache (\texttt{KV} \texttt{cache}) compression has emerged as a promising technique to optimize Large Language Model (LLM) serving. It primarily decreases the memory consumption of \texttt{KV} \texttt{cache} to reduce the…

Machine Learning · Computer Science 2025-04-01 Wei Gao , Xinyu Zhou , Peng Sun , Tianwei Zhang , Yonggang Wen

While scaling laws have been continuously validated in large language models (LLMs) with increasing model parameters, the inherent tension between the inference demands of LLMs and the limited resources of edge devices poses a critical…

Serving numerous users and requests concurrently requires good fairness in Large Language Models (LLMs) serving system. This ensures that, at the same cost, the system can meet the Service Level Objectives (SLOs) of more users , such as…

Machine Learning · Computer Science 2024-11-28 Ao Shen , Zhiyao Li , Mingyu Gao

Inference-time compute has re-emerged as a practical way to improve LLM reasoning. Most test-time scaling (TTS) algorithms rely on autoregressive decoding, which is ill-suited to discrete diffusion language models (dLLMs) due to their…

Machine Learning · Computer Science 2026-05-06 Jinbin Bai , Yixuan Li , Yuchen Zhu , Yi Xin , Qingyu Shi , Aosong Feng , Xiaohong Liu , Molei Tao , Jianru Xue , Xiangtai Li , Ming-Hsuan Yang

Designing efficient optimizers for large language models (LLMs) with low-memory requirements and fast convergence is an important and challenging problem. This paper makes a step towards the systematic design of such optimizers through the…

Machine Learning · Computer Science 2025-02-21 Wenbo Gong , Meyer Scetbon , Chao Ma , Edward Meeds

Whether attention key value (KV) states computed for one prompt for a small LLM can be reused to accelerate inference on a new similar prompt, giving an increase to the space to its context memory using an approach called token recycling.…

Machine Learning · Computer Science 2025-12-16 Prashant Pandey

Running Large Language Models (LLMs) on edge devices is crucial for reducing latency, improving real-time processing, and enhancing privacy. By performing inference directly on the device, data does not need to be sent to the cloud,…

Hardware Architecture · Computer Science 2025-10-21 Tianhua Xia , Sai Qian Zhang

Modern large language models (LLMs) increasingly rely on inference-time planning and external tools to improve reasoning. We benchmark this behavior on two real-world settings: event-centric question answering over graph-structured…

Computation and Language · Computer Science 2026-03-06 Subha Ghoshal , Ali Al-Bustami

The efficiency of large language models (LLMs) remains a critical challenge, particularly in contexts where computational resources are limited. Traditional attention mechanisms in these models, while powerful, require significant…

Computation and Language · Computer Science 2024-07-19 Bingli Liao , Danilo Vasconcellos Vargas

The growing complexity of network traffic and demand for ultra-low latency communication require smarter packet traffic management. Existing Deep Learning-based queuing approaches struggle with dynamic network scenarios and demand high…

Networking and Internet Architecture · Computer Science 2025-09-03 Shiva Raj Pokhrel , Deol Satish , Jonathan Kua , Anwar Walid

Serverless Large Language Models (LLMs) have emerged as a cost-effective solution for deploying AI services by enabling a 'pay-as-you-go' pricing model through GPU resource sharing. However, cold-start latency, especially the model loading…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-02 Wenbin Zhu , Zhaoyan Shen , Zili Shao , Hongjun Dai , Feng Chen