论文研究
arxiv.org ·
生产扩散模型推理服务中 LoRA 适配器的共现模式
论文基于阿里生产扩散模型推理数据集 GenTD26，用图论方法构建适配器共现网络，从静态结构与动态演化两方面刻画。主要发现：共现网络极度稀疏，适配器使用频率呈显著重尾分布；引入首个适配器带来 66.1% 执行延迟开销，之后边际成本递减；共现关系由基础模型驱动，90.6% 的多适配器请求共享同一主模型，66.2% 的显著共现边连接同模型适配器对，85.8% 的多适配器请求中所有适配器对形成显著共现边；适配器生态呈核心—边缘双极结构，模型级周 Jaccard 相似度为 0.696，top-10 热门模型在 12 小时窗口内流失率达 54.5%。作者据此提出基于 top-k 共现统计的预加载策略，离线实验在 k=3 时覆盖 81.0% 测试集共现对，并通过频率阈值与时间窗口的敏感性分析验证结论稳健性，为 LoRA 推理服务的缓存预加载、自适应调度与 GPU 显存管理提供数据驱动依据。
AI推荐理由 基于阿里生产扩散模型推理数据集 GenTD26 的实证研究，给出可验证的量化结论：共现网络极度稀疏、适配器使用频率呈重尾分布；引入首个适配器带来 66.1% 执行延迟开销且边际成本递减；90.6% 多适配器请求共享同一主模型；模型级周 Jaccard 相似度 0.696，top-10 热门模型 12 小时窗口流失率 54.5%；基于 top-k 共现统计的预加载策略在 k=3 时覆盖 81.0% 测试集共现对。对 LoRA 推理服务的缓存预加载、调度与显存管理有直接参考价值。局限：结论来自单一厂商生产数据集，离线实验未报告线上部署效果，需谨慎外推。
78
正文
Computer Science > Distributed, Parallel, and Cluster Computing
arXiv:2609.23321 (cs)
[Submitted on 20 Sep 2026]
Title:Co-occurrence Patterns of LoRA Adapters in Production Diffusion Model Inference Services
Authors:Tao Zhang, Bin Liao, Tao Zhou, Yanping Liu
View a PDF of the paper titled Co-occurrence Patterns of LoRA Adapters in Production Diffusion Model Inference Services, by Tao Zhang and 3 other authors
View PDF
HTML (experimental)
Abstract:Low-rank adaptation (LoRA) has become a key technology for serving large-scale personalized large language models and diffusion models in the cloud. However, the co-occurrence patterns, resource contention relationships, and evolutionary regularities of adapters under production inference workloads have not been systematically or quantitatively studied. Based on GenTD26, Alibaba's production diffusion model inference dataset, this paper adopts a graph-theoretic framework to construct an adapter co-occurrence network and conducts a characterization from both static structure and dynamic evolution. Our main findings are as follows. (1) The co-occurrence network is extremely sparse, and adapter usage frequency follows a significant heavy-tailed distribution. (2) Introducing the first adapter incurs a 66.1% execution-latency overhead, with diminishing marginal costs afterwards. (3) Co-occurrence relationships are driven by base models: in 90.6% of multi-adapter requests, all adapters share the same dominant base model; 66.2% of significant co-occurrence edges connect same-model adapter pairs; and in 85.8% of multi-adapter requests, all adapter pairs form significant co-occurrence edges. (4) The adapter ecosystem exhibits a core-periphery bipolar structure, with a weekly Jaccard similarity of 0.696 at the model level and a churn rate of 54.5% for the top-10 hottest models within a 12-hour window. Based on these findings, we propose a preloading strategy built on top-k co-occurrence statistics; offline experiments show that it covers 81.0% of test-set co-occurrence pairs at k=3, and sensitivity analyses across frequency thresholds and time windows verify the robustness of the conclusions. These results provide a data-driven basis for cache preloading, adaptive scheduling, and GPU memory management in LoRA inference services.
Comments:
Subjects:
Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as:
arXiv:2609.23321 [cs.DC]
(or
arXiv:2609.23321v1 [cs.DC] for this version)
https://doi.org/10.48550/arXiv.2609.23321
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Bin Liao [view email]
[v1]
Sun, 20 Sep 2026 03:16:26 UTC (4,719 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Co-occurrence Patterns of LoRA Adapters in Production Diffusion Model Inference Services, by Tao Zhang and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.DC
new
|
recent
| 2026-09
Change to browse by:
cs
cs.AI
cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)