Search papers, labs, and topics across Lattice.
This paper addresses the Foundation Model Deployment Portfolio (FMDP) problem in transportation management by optimizing the deployment of various foundation models under shared hardware constraints. By formulating the problem as a mixed-integer program, the authors minimize the total cost of ownership while satisfying quality, latency, and safety requirements across multiple TMC functions. The proposed greedy heuristic achieves a cost-effective solution, demonstrating a $34/month portfolio that significantly undercuts traditional all-closed-API approaches by 97%.
A mixed portfolio of foundation models can slash deployment costs for transportation management by 97%, revolutionizing how TMCs utilize AI.
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.
