为交通管理中心优化模型部署组合，大幅降低算力成本。
Cost-Optimal Foundation Model Deployment Portfolio for Transportation Management
- 构建混合整数规划模型，统筹多任务需求与硬件预算
- 实测成本降至最低仅34美元/月，比最便宜的纯云端方案低97%
- 适合需在成本与性能间权衡的交通系统管理者
基础模型（如大语言模型和视觉语言模型）正被广泛应用于交通管理中心（TMC）的异常检测、事件报告和出行信息服务等任务。在多个功能上部署多种模型时，需回答：每个功能应选择哪个模型、采用何种部署方式，在共享GPU预算下如何配置？本文将此问题建模为基础模型部署组合（FMDP）问题，目标是最小化总拥有成本（TCO），同时满足各功能的质量、延迟和安全约束。证明该问题是NP-hard，并提出一种多项式时间的贪心启发式算法。在包含五个TMC功能和19个（模型, 部署模式）候选方案的案例研究中，FMDP识别出一个混合部署方案，每月成本仅34美元（比最便宜的纯闭源API方案低97%），其中四个功能通过开源API处理，剩余一个因开源模型质量不达标而使用闭源API。盈亏平衡分析显示，自建GPU投资在每小时超过约309次视觉查询或API价格翻倍后才具合理性。
原文摘要 · Abstract (English)
Foundation models, including large language models (LLMs) and vision-language models (VLMs), are increasingly used for transportation management center (TMC) tasks such as anomaly detection, incident reporting, and traveler information. Deploying multiple such models across TMC functions raises a portfolio question: which model should serve each function, in which deployment mode, and under what shared hardware budget? We formulate this as the Foundation Model Deployment Portfolio (FMDP) problem, a mixed-integer program minimizing total cost of ownership (TCO) subject to per-function quality, latency, and safety constraints over shared GPU capacity. We prove the problem NP-hard by reduction from the 0-1 knapsack problem and propose a polynomial-time greedy heuristic. In an illustrative case study with five TMC functions and 19 candidate (model, mode) pairs, FMDP identifies a mixed portfolio costing $34/mo (97% below the cheapest feasible all-closed-API baseline) by routing four functions to open-source APIs and the one function whose quality floor no open-source model meets to a closed API. Break-even analysis shows that on-premise GPU investment becomes reasonable only above approximately 309 vision queries/hour or if API prices double.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。