English
Related papers

Related papers: STAR: Decode-Phase Rescheduling for LLM Inference

200 papers

To meet strict Service-Level Objectives (SLOs),contemporary Large Language Models (LLMs) decouple the prefill and decoding stages and place them on separate GPUs to mitigate the distinct bottlenecks inherent to each phase. However, the…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-10 Junhan Liao , Minxian Xu , Wanyi Zheng , Yan Wang , Kejiang Ye , Rajkumar Buyya , Chengzhong Xu

Efficient inference in large language models (LLMs) has become a critical focus as their scale and complexity grow. Traditional autoregressive decoding, while effective, suffers from computational inefficiencies due to its sequential token…

Computation and Language · Computer Science 2024-11-28 Hyun Ryu , Eric Kim

Although Large Language Models (LLMs) achieve remarkable performance across various tasks, they often struggle with complex reasoning tasks, such as answering mathematical questions. Recent efforts to address this issue have primarily…

Machine Learning · Computer Science 2024-06-27 Jikun Kang , Xin Zhe Li , Xi Chen , Amirreza Kazemi , Qianyi Sun , Boxing Chen , Dong Li , Xu He , Quan He , Feng Wen , Jianye Hao , Jun Yao

Speculative decoding, which combines a draft model with a target model, has emerged as an effective approach to accelerate large language model (LLM) inference. However, existing methods often face a trade-off between the acceptance rate…

Computation and Language · Computer Science 2025-05-14 Danying Ge , Jianhua Gao , Qizhi Jiang , Yifei Feng , Weixing Ji

Large language models (LLMs) have become proficient at solving a wide variety of tasks, including those involving multi-modal inputs. In particular, instantiating an LLM (such as LLaMA) with a speech encoder and training it on paired data…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-13 Desh Raj , Gil Keren , Junteng Jia , Jay Mahadeokar , Ozlem Kalinli

We study the problem of optimizing Large Language Model (LLM) inference scheduling to minimize total latency. LLM inference is an online and multi-task service process and also heavily energy consuming by which a pre-trained LLM processes…

Machine Learning · Computer Science 2025-09-03 Zixi Chen , Yinyu Ye , Zijie Zhou

Decoding with autoregressive large language models (LLMs) traditionally occurs sequentially, generating one token after another. An emerging line of work explored parallel decoding by identifying and simultaneously generating semantically…

Nowadays, Large Language Models (LLMs) have been gradually employed to solve complex tasks. To face the challenge, task decomposition has become an effective way, which proposes to divide a complex task into multiple simpler subtasks and…

Computation and Language · Computer Science 2025-04-14 Yiliu Sun , Yanfang Zhang , Zicheng Zhao , Sheng Wan , Dacheng Tao , Chen Gong

Large language models (LLMs) have revolutionized applications such as code completion, chatbots, and online classification. To elevate user experiences, service level objectives (SLOs) serve as crucial benchmarks for assessing inference…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-13 Jinqi Huang , Yi Xiong , Xuebing Yu , Wenjie Huang , Entong Li , Li Zeng , Xin Chen

The emergence of reasoning-based LLMs leveraging Chain-of-Thought (CoT) inference introduces new serving challenges, as their extended reasoning phases delay user-visible output and inflate Time-To-First-Token (TTFT). Existing LLM serving…

Machine Learning · Computer Science 2026-02-13 Eunyeong Cho , Jehyeon Bang , Ranggi Hwang , Minsoo Rhu

Large reasoning models (LRMs) achieve state-of-the-art performance by generating long chains-of-thought, but often waste computation on redundant reasoning after the correct answer has already been reached. We introduce Early-Stopping for…

Artificial Intelligence · Computer Science 2026-02-11 Junda Wang , Zhichao Yang , Dongxu Zhang , Sanjit Singh Batra , Robert E. Tillman

Large Language Models (LLMs), constrained by their auto-regressive nature, suffer from slow decoding. Speculative decoding methods have emerged as a promising solution to accelerate LLM decoding, attracting attention from both systems and…

Artificial Intelligence · Computer Science 2026-02-03 Xuliang Wang , Yuetao Chen , Maochan Zhen , Fang Liu , Xinzhou Zheng , Xingwu Liu , Hong Xu , Ming Li

Conventional research on large language models (LLMs) has primarily focused on refining output distributions, while paying less attention to the decoding process that transforms these distributions into final responses. Recent advances,…

Computation and Language · Computer Science 2025-10-28 Chenheng Zhang , Tianqi Du , Jizhe Zhang , Mingqing Xiao , Yifei Wang , Yisen Wang , Zhouchen Lin

This paper presents "Predictive Pipelined Decoding (PPD)," an approach that speeds up greedy decoding in Large Language Models (LLMs) while maintaining the exact same output as the original decoding. Unlike conventional strategies, PPD…

Computation and Language · Computer Science 2024-07-30 Seongjun Yang , Gibbeum Lee , Jaewoong Cho , Dimitris Papailiopoulos , Kangwook Lee

Large Language Models (LLMs) have transformed code auto-completion by generating context-aware suggestions. Yet, deciding when to present these suggestions remains underexplored, often leading to interruptions or wasted inference calls. We…

Software Engineering · Computer Science 2026-02-10 Mohammad Nour Al Awad , Sergey Ivanov , Olga Tikhonova

Large language models (LLMs) have revolutionized the field of AI, demonstrating unprecedented capacity across various tasks. However, the inference process for LLMs comes with significant computational costs. In this paper, we propose an…

Computation and Language · Computer Science 2023-05-30 Zangwei Zheng , Xiaozhe Ren , Fuzhao Xue , Yang Luo , Xin Jiang , Yang You

Speculative decoding (SD) accelerates large language model (LLM) inference by using a smaller draft model to propose multiple tokens that are verified by a larger target model in parallel. While prior work demonstrates substantial speedups…

Machine Learning · Computer Science 2026-05-15 Linghao Kong , Megan Flynn , Michael Peng , Nir Shavit , Mark Kurtz , Alexandre Marques

Large language models (LLMs) achieve state-of-the-art accuracy on complex reasoning tasks by generating multiple chain-of-thought (CoT) traces, but using a fixed token budget per query leads to over-computation on easy inputs and…

Artificial Intelligence · Computer Science 2026-02-03 Katrina Brown , Aneesh Muppidi , Rana Shahout

The rapid evolution of Large Language Model (LLM) inference systems has yielded significant efficiency improvements. However, our systematic analysis reveals that current evaluation methodologies frequently exhibit fundamental flaws, often…

Looped Language Models (LoopLMs) enable efficient latent reasoning through depth recurrence, yet exhibit unreliable test-time scaling behavior: performance often peaks at a certain iteration depth and then collapses with further recurrence.…

Machine Learning · Computer Science 2026-05-27 Xiao-Wen Yang , Ziyu Han , Xi-Hua Zhang , Wen-Da Wei , Jie-Jing Shao , Lan-Zhe Guo , Yu-Feng Li