paper-with-me

홈 › Papers

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference

2025-05-29 · Yinghao Tang, Tingfeng Lan, Xiuqi Huang, Hui Lu, Wei Chen

Existing Large Language Model (LLM) serving systems prioritize maximum throughput. They often neglect Service Level Objectives (SLOs) such as Time to First Token (TTFT) and Time Per Output Token (TPOT), which leads to suboptimal SLO attainment. This paper introduces SCORPIO, an SLO-oriented LLM serving system designed to maximize system goodput and SLO attainment for workloads with heterogeneous SLOs. Our core insight is to exploit SLO heterogeneity for adaptive scheduling across admission control, queue management, and batch selection. SCORPIO features a TTFT Guard, which employs least-deadline-first reordering and rejects unattainable requests, and a TPOT Guard, which utilizes a VBS-based admission control and a novel credit-based batching mechanism. Both guards are supported by a predictive module. Evaluations demonstrate that SCORPIO improves system goodput by up to 14.4X and SLO adherence by up to 46.5% compared to state-of-the-art baselines.

📄 PDF Abstract BibTeX arXiv:2505.23022

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language ModelManagementScheduling

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Similar Papers 제목 키워드 기반

Thinking Short and Right Over Thinking Long: Serving LLM Reasoning Efficiently and Accurately

2025-05-19 · Yuhang Wang, Youhe Jiang, Bin Cui, Fangcheng Fu

Recent advances in test-time scaling suggest that Large Language Models (LLMs) can gain better capabilities by generating Chain-of-Thought reasoning (analogous to human thinking) to respond a given request, and meanwhile…

Avoiding Copyright Infringement via Large Language Model Unlearning

2024-06-16 · Guangyao Dou, Zheyuan Liu, Qing Lyu, Kaize Ding 외

Pre-trained Large Language Models (LLMs) have demonstrated remarkable capabilities but also pose risks by learning and generating copyrighted material, leading to significant legal and ethical concerns. In real-world sce…

General KnowledgeLanguage ModelingLanguage ModellingLarge Language Model+1

Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten

2023-02-08 · Satyapriya Krishna, Jiaqi Ma, Himabindu Lakkaraju

The Right to Explanation and the Right to be Forgotten are two important principles outlined to regulate algorithmic decision making and data usage in real-world applications. While the right to explanation allows indivi…

Decision Making

SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation

2024-06-18 · Xiaoze Liu, Ting Sun, Tianyang Xu, Feijie Wu 외

Large Language Models (LLMs) have transformed machine learning but raised significant legal concerns due to their potential to produce text that infringes on copyrights, resulting in several high-profile lawsuits. The le…

Text Generation

Novel scorpion detection system combining computer vision and fluorescence

2021-08-09 · Francisco Luis Giambelluca, Jorge Osio, Luis A. Giambelluca, Marcelo A. Cappelletti

In this work, a fully automatic and real-time system for the detection of scorpions was developed using computer vision and deep learning techniques. This system is based on the implementation of a double validation proc…