CLAIDCLGApr 28, 2025

Taming the Titans: A Survey of Efficient LLM Inference Serving

arXiv:2504.19720v120 citationsh-index: 19
Originality Synthesis-oriented
AI Analysis

It tackles the problem of efficient LLM inference serving for researchers and practitioners, but is incremental as it synthesizes existing work rather than introducing new methods.

This survey addresses the challenge of achieving low latency and high throughput in LLM inference services due to memory and computational demands, by comprehensively reviewing recent methods across instance-level, cluster-level, and emerging scenarios.

Large Language Models (LLMs) for Generative AI have achieved remarkable progress, evolving into sophisticated and versatile tools widely adopted across various domains and applications. However, the substantial memory overhead caused by their vast number of parameters, combined with the high computational demands of the attention mechanism, poses significant challenges in achieving low latency and high throughput for LLM inference services. Recent advancements, driven by groundbreaking research, have significantly accelerated progress in this field. This paper provides a comprehensive survey of these methods, covering fundamental instance-level approaches, in-depth cluster-level strategies, emerging scenario directions, and other miscellaneous but important areas. At the instance level, we review model placement, request scheduling, decoding length prediction, storage management, and the disaggregation paradigm. At the cluster level, we explore GPU cluster deployment, multi-instance load balancing, and cloud service solutions. For emerging scenarios, we organize the discussion around specific tasks, modules, and auxiliary methods. To ensure a holistic overview, we also highlight several niche yet critical areas. Finally, we outline potential research directions to further advance the field of LLM inference serving.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes