TimelyLLM: Segmented LLM Serving System for Time-sensitive Robotic Applications

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ling, Neiwen, Chen, Guojun, Zhong, Lin
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912169930522624
author Ling, Neiwen
Chen, Guojun
Zhong, Lin
author_facet Ling, Neiwen
Chen, Guojun
Zhong, Lin
contents Large Language Models (LLMs) such as GPT-4 and Llama3 can already comprehend complex commands and process diverse tasks. This advancement facilitates their application in controlling drones and robots for various tasks. However, existing LLM serving systems typically employ a first-come, first-served (FCFS) batching mechanism, which fails to address the time-sensitive requirements of robotic applications. To address it, this paper proposes a new system named TimelyLLM serving multiple robotic agents with time-sensitive requests. TimelyLLM introduces novel mechanisms of segmented generation and scheduling that optimally leverage redundancy between robot plan generation and execution phases. We report an implementation of TimelyLLM on a widely-used LLM serving framework and evaluate it on a range of robotic applications. Our evaluation shows that TimelyLLM improves the time utility up to 1.97x, and reduces the overall waiting time by 84%.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18695
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TimelyLLM: Segmented LLM Serving System for Time-sensitive Robotic Applications
Ling, Neiwen
Chen, Guojun
Zhong, Lin
Robotics
Distributed, Parallel, and Cluster Computing
Machine Learning
Large Language Models (LLMs) such as GPT-4 and Llama3 can already comprehend complex commands and process diverse tasks. This advancement facilitates their application in controlling drones and robots for various tasks. However, existing LLM serving systems typically employ a first-come, first-served (FCFS) batching mechanism, which fails to address the time-sensitive requirements of robotic applications. To address it, this paper proposes a new system named TimelyLLM serving multiple robotic agents with time-sensitive requests. TimelyLLM introduces novel mechanisms of segmented generation and scheduling that optimally leverage redundancy between robot plan generation and execution phases. We report an implementation of TimelyLLM on a widely-used LLM serving framework and evaluate it on a range of robotic applications. Our evaluation shows that TimelyLLM improves the time utility up to 1.97x, and reduces the overall waiting time by 84%.
title TimelyLLM: Segmented LLM Serving System for Time-sensitive Robotic Applications
topic Robotics
Distributed, Parallel, and Cluster Computing
Machine Learning
url https://arxiv.org/abs/2412.18695