NVIDIA / NVIDIA/cuopt

[QST] High GPU memory usage when solving CVRP

Open
#250 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

question
Dominant language
Cuda
Stars
1k
Forks
233
Avg merge
4d 4h
Merged PRs (30d)
95

Description

Hi! Could you please briefly explain why the routing algorithm consumes so much GPU memory during solving? I observe ~16GB usage for a CVRP instance with 13,000 orders on an NVIDIA T4.

Thanks in advance!

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the CVRP solve with 13,000 orders on an NVIDIA T4 and measure GPU memory use during solving. Review the solver's memory behavior and determine whether the roughly 16 GB usage is expected; done means providing a clear explanation grounded in the observed measurements.

Written by the indexing model from the issue text.

Assessment

Domain
performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.