NVIDIA cuOpt™ is a GPU-accelerated solver that uses heuristics and metaheuristics to solve complex vehicle routing problem variants with a wide range of constraints.

NVIDIA cuOpt is an Operations Research optimization API using AI to help developers create complex, real-time fleet routing workflows on NVIDIA GPUs.
The route optimization workflow demonstrates how to use NVIDIA cuOpt to minimize vehicle routing inefficiencies by finding the most optimal route for a fleet of vehicles making deliveries, pickups, dispatching jobs, etc.
Pizza giant taps NVIDIA GPUs to bring AI to your neighborhood store.
Promising more timely deliveries for consumers around the globe, NVIDIA’s cuOpt real-time route optimization software has set records on a key route optimization benchmark.
Last-mile delivery is the most expensive part of supply chain costs. Companies need vehicle routing solutions with additional retail constraints to reduce these costs. Larger problems might take longer and produce sub-optimal results. This can be a big burden and cost for changing requirements and constraints. We’ll describe how to accelerate vehicle routing algorithms with GPUs to obtain good solutions in a reasonable time.
Telcos have some of the largest datasets in the world. AT&T’s Data Science Team will pull back the curtain on a series of use cases that have been accelerated using GPUs and NVIDIA AI tools/frameworks. They’ll talk through their analysis and use of NVIDIA capabilities across different domains and share specific use case examples, their efficiency gains, and corresponding business impacts.
The goal of the vehicle routing problem (VRP) is to identify an optimal set of routes for a fleet of vehicles visiting multiple delivery locations. The changing economic and geopolitical scenario has made last-mile delivery one of the most challenging and expensive tasks of the logistics fulfillment cycle.