NVIDIA/cuopt-examples

NVIDIA cuOpt examples for decision optimization

What it solves

It provides practical implementations and demonstrations of how to use NVIDIA cuOpt to solve complex decision optimization problems. It specifically addresses the challenge of finding optimal solutions for Mixed Integer Programming, Linear Programming, and Vehicle Routing problems using GPU acceleration.

How it works

The repository serves as a collection of examples and notebooks that interface with the cuOpt engine via service APIs, an SDK, and integrations with other open-source optimization packages. Users can deploy the environment using Docker images tailored for different CUDA versions to run these optimization workflows in Jupyter notebooks.

Who it’s for

Developers and researchers working on logistics, supply chain, and industrial automation who need to solve large-scale optimization problems efficiently using NVIDIA GPUs.

Highlights

  • GPU-accelerated solving for Mixed Integer Programming and Linear Programming.
  • Specialized support for Vehicle Routing problems.
  • Includes a specific example for optimizing Autonomous Mobile Robot (AMR) routes in factories using a Capacitated Pickup and Delivery Problem with Time Windows (CPDPTW) model.
  • Ready-to-run Docker containers for quick setup.

Related

  • Project
    NVIDIA/cuopt

    A GPU-accelerated optimization engine for solving large-scale linear, quadratic, and vehicle routing problems in near real-time.

  • Project
    NVIDIA-AI-Blueprints/portfolio-optimization

    A GPU-accelerated portfolio optimization framework that uses NVIDIA cuOpt and RAPIDS cuML to speed up scenario generation and Mean-CVaR risk modeling.

  • Project
    NVIDIA/Model-Optimizer

    NVIDIA Model Optimizer (ModelOpt) is an open‑source Python library that lets you apply quantization, pruning, NAS, distillation, speculative decoding, and sparsity to Hugging Face, PyTorch, or ONNX models and export them for fast inference with NVIDIA runtimes like TensorRT‑LLM, vLLM, and SGLang.

  • Project
    NVIDIA/CUDALibrarySamples

    A collection of GPU-accelerated examples demonstrating the use of NVIDIA CUDA libraries for high-performance math, image processing, and linear algebra.

  • Project
    neka-nat/cupoch

    A GPU-accelerated library for rapid 3D data processing in robotics, providing high-performance point cloud algorithms, collision avoidance, and path planning.