English
Related papers

Related papers: Enabling Efficient Batch Serving for LMaaS via Gen…

200 papers

Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhibit extensive redundancy from overlapping prompts and…

Multiagent Systems · Computer Science 2026-03-18 Noppanat Wadlom , Junyi Shen , Yao Lu

The emergence of large language models (LLMs) has revolutionized the capabilities of text comprehension and generation. Multi-modal generation attracts great attention from both the industry and academia, but there is little work on…

Information Retrieval · Computer Science 2024-04-16 Xiaoteng Shen , Rui Zhang , Xiaoyan Zhao , Jieming Zhu , Xi Xiao

Large Language Models (LLMs) have achieved unprecedented success across various applications, but their substantial memory requirements pose significant challenges to current memory system designs, especially during inference. Our work…

Hardware Architecture · Computer Science 2025-12-02 Zhongchun Zhou , Chengtao Lai , Wei Zhang

Training and serving long-context large language models (LLMs) incurs substantial overhead. To address this, two critical steps are often required: a pretrained LLM typically undergoes a separate stage for context length extension by…

Computation and Language · Computer Science 2024-12-06 Suyu Ge , Xihui Lin , Yunan Zhang , Jiawei Han , Hao Peng

Large Language Models (LLMs) leverage external tools primarily through generating the API request to enhance task completion efficiency. The accuracy of API request generation significantly determines the capability of LLMs to accomplish…

Software Engineering · Computer Science 2024-10-10 Huanxi Liu , Jiaqi Liao , Dawei Feng , Kele Xu , Huaimin Wang

With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retrieved passages lead large prompts and therefore, compute…

Information Retrieval · Computer Science 2026-04-06 Cornelius Kummer , Lena Jurkschat , Michael Färber , Sahar Vahdati

Performing inference on large volumes of samples with large language models (LLMs) can be computationally and financially costly in industry and real-world use. We propose batch prompting, a simple yet effective prompting approach that…

Computation and Language · Computer Science 2023-10-25 Zhoujun Cheng , Jungo Kasai , Tao Yu

Scaling up data, parameters, and test-time computation has been the mainstream methods to improve LLM systems (LLMsys), but their upper bounds are almost reached due to the gradual depletion of high-quality data and marginal gains obtained…

Machine Learning · Computer Science 2026-05-12 Qingyao Ai , Yichen Tang , Changyue Wang , Jianming Long , Weihang Su , Yiqun Liu

Generative AI like the Large Language Models (LLMs) has become more available for the general consumer in recent years. Publicly available services, e.g., ChatGPT, perform token generation on networked cloud server hardware, effectively…

Machine Learning · Computer Science 2024-12-23 Liam Seymour , Basar Kutukcu , Sabur Baidya

Large Language Model (LLM) applications have emerged as a prominent use case for Function-as-a-Service (FaaS) due to their high computational demands and sporadic invocation patterns. However, serving LLM functions within FaaS frameworks…

Operating Systems · Computer Science 2025-03-11 Weihao Cui , Ziyi Xu , Han Zhao , Quan Chen , Zijun Li , Bingsheng He , Minyi Guo

Prompt engineering enables Large Language Models (LLMs) to perform a variety of tasks. However, lengthy prompts significantly increase computational complexity and economic costs. To address this issue, we study six prompt compression…

Computation and Language · Computer Science 2025-05-02 Zheng Zhang , Jinyi Li , Yihuai Lan , Xiang Wang , Hao Wang

As the ever-increasing token limits of large language models (LLMs) have enabled long context as input, prompting with single data samples might no longer an efficient way. A straightforward strategy improving efficiency is to batch data…

Computation and Language · Computer Science 2024-07-16 Jianzhe Lin , Maurice Diesendruck , Liang Du , Robin Abraham

Code Large Language Models (CodeLLMs) are increasingly integrated into modern software development workflows, yet efficiently serving them in resource-constrained, self-hosted environments remains a significant challenge. Existing LLM…

Software Engineering · Computer Science 2025-06-26 Shi Chang , Boyuan Chen , Kishanthan Thangarajah , Hanan Lutfiyya , Ahmed E. Hassan

The planning ability of Large Language Models (LLMs) has garnered increasing attention in recent years due to their remarkable capacity for multi-step reasoning and their ability to generalize across a wide range of domains. While some…

Artificial Intelligence · Computer Science 2025-02-19 Mohamed Aghzal , Erion Plaku , Gregory J. Stein , Ziyu Yao

Large Language Models (LLM) are increasingly being explored for problem-solving tasks. However, their strategic planning capability is often viewed with skepticism. Recent studies have incorporated the Monte Carlo Tree Search (MCTS)…

Artificial Intelligence · Computer Science 2025-02-05 Bingzheng Gan , Yufan Zhao , Tianyi Zhang , Jing Huang , Yusu Li , Shu Xian Teo , Changwang Zhang , Wei Shi

With the rapid adoption of Large Language Models (LLMs), LLM-adapters have become increasingly common, providing lightweight specialization of large-scale models. Serving hundreds or thousands of these adapters on a single GPU allows…

Function calling is a fundamental capability of today's large language models, but sequential function calling posed efficiency problems. Recent studies have proposed to request function calls with parallelism support in order to alleviate…

Software Engineering · Computer Science 2025-10-30 Xiaoxia Liu , Peng Di , Cong Li , Jun Sun , Jingyi Wang

Large language models (LLMs) are increasingly used to assist ideation in research, but evaluating the quality of LLM-generated research proposals remains difficult: novelty and soundness are hard to measure automatically, and large-scale…

Computation and Language · Computer Science 2026-05-27 Heng Wang , Pengcheng Jiang , Jiashuo Sun , Zhiyi Shi , Haofei Yu , Jiawei Han , Heng Ji

Function as a Service (FaaS) permits cloud customers to deploy to cloud individual functions, in contrast to complete virtual machines or Linux containers. All major cloud providers offer FaaS products (Amazon Lambda, Google Cloud…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-08-12 Pawel Zuk , Krzysztof Rzadca

In this paper, we first show that increases in beam size, even for small-sized LLMs (1B-7B params), require extensive GPU usage, leading to up to 80% of recurring crashes due to memory overloads in LLM-based APR. Seemingly simple solutions…

Software Engineering · Computer Science 2025-10-20 Thanh Le-Cong , Bach Le , Toby Murray