arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.06646cs.DC
收藏

多实例GPU上的最优工作负载放置

Optimal Workload Placement on Multi-Instance GPUs

Bekir Turkkan, Pavankumar Murali, Pavithra Harsha, Rohan Arora, Gerard Vanloo, Chandra Narayanaswami

AI总结:

针对支持MIG分区的GPU,本文研究LLM推理工作负载的最优放置与迁移,提出优化方法和启发式方法,显著减少GPU使用数量及资源浪费。

摘要:

目前迫切需要优化图形处理器(GPU)的使用,GPU可以说已成为最昂贵、最受追捧的IT资源之一。为帮助实现这一目标,当前一代的若干GPU支持一种名为Multi-Instance GPU(MIG,多实例GPU)的分区功能,允许多个工作负载共享一块GPU,但存在一些约束。本文研究如何在GPU上优化放置基于Large Language Model(LLM,大语言模型)的AI推理工作负载。我们首先识别并给出实践中遇到的若干用例,这些用例要求高效放置工作负载,或将其迁移到其他GPU,从而为传入的工作负载腾出空间。总体目标是使用尽可能少的GPU,并进一步最小化已使用GPU上的内存和计算浪费。我们开发了两种方法来解决该问题:一种优化方法和一种启发式方法。我们针对多个用例,将这些方法与两种工作负载调度启发式算法进行基准比较。结果表明,与基线启发式算法相比,所用GPU数量最高改善2.85倍,GPU浪费最高减少70%。我们计划使SRE社区能够在生产环境中利用我们提出的方法。

英文摘要:

There is an urgent and pressing need to optimize usage of Graphical Processing Units (GPUs), which have arguably become one of the most expensive and sought after IT resources. To help with this goal, several of the current generation of GPUs support a partitioning feature, called Multi-Instance GPU (MIG) to allow multiple workloads to share a GPU, albeit with some constraints. In this paper we investigate how to optimize the placement of Large Language Model (LLM)-based AI Inferencing workloads on GPUs. We first identify and present several use cases that are encountered in practice that require workloads to be efficiently placed or migrated to other GPUs to make room for incoming workloads. The overarching goal is to use as few GPUs as possible and to further minimize memory and compute wastage on GPUs that are utilized. We have developed two approaches to address this problem: an optimization method and a heuristic method. We benchmark these with two workload scheduling heuristics for multiple use cases. Our results show up to 2.85x improvement in the number of GPUs used and up to 70% reduction in GPU wastage over baseline heuristics. We plan to enable the SRE community to leverage our proposed method in production environments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑