---
format: "aidr-story-markdown/v1"
id: "6e431623ea977add800b4ec768f3e1818fbebc0555496f851201f4d060522808"
canonical_url: "https://aidr.today/6e431623?lang=en"
title: "Scaling Decision Optimization to 100 Million Variables and Beyond with mPDLP in NVIDIA cuOpt"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-07T15:45:00.000Z"
category: "Frameworks"
topics: ["nvidia","framework"]
source_urls: ["https://developer.nvidia.com/blog/scaling-decision-optimization-to-100-million-variables-and-beyond-with-mpdlp-in-nvidia-cuopt/"]
summary: "NVIDIA cuOpt GPU-accelerated decision optimization can deliver speedups of more than 10x over CPU solvers on a single GPU for large-scale linear programming problems. cuOpt is now solving the zib03 benchmark, which has over 104 million nonzeros, on multiple GPUs with mPDLP, achieving a solve rate nearly 10x faster than a year before."
---

# Scaling Decision Optimization to 100 Million Variables and Beyond with mPDLP in NVIDIA cuOpt

> [Open the canonical story](<https://aidr.today/6e431623?lang=en>)

**Published:** 2026-10-07T15:45:00.000Z
**Category:** Frameworks
**Topics:** nvidia, framework

## Summary

NVIDIA cuOpt GPU\-accelerated decision optimization can deliver speedups of more than 10x over CPU solvers on a single GPU for large\-scale linear programming problems\. cuOpt is now solving the zib03 benchmark, which has over 104 million nonzeros, on multiple GPUs with mPDLP, achieving a solve rate nearly 10x faster than a year before\.

## Sources

- [Story source](<https://developer.nvidia.com/blog/scaling-decision-optimization-to-100-million-variables-and-beyond-with-mpdlp-in-nvidia-cuopt/>)