NVIDIA / NVIDIA/cuopt

[FEA] Web-hosted cuopt client interface

Open
#479 16 comments 0 reactions 1 assignee View on GitHub

@Iroy30 is already working on this.

Since Oct 9, 2025.

awaiting response feature request
Dominant language
Cuda
Stars
1k
Forks
233
Avg merge
4d 4h
Merged PRs (30d)
95

Description

Is your feature request related to a problem? Please describe.
The python client's current implementation CuOptServiceSelfHostClient assumed that the model can only be interacted through local hosting or exposed IP and port endpoint. However, extending the current functionality to support web-hosted cuopt model is very trivial as the current interaction is done through request library

Describe the solution you'd like
Additional class CuOptServiceWebHostedClient which extends the base CuOptServiceSelfHostClient and re-use most functionalities

Describe alternatives you've considered
Alternative considered is to remove the authentication layer from the web hosted endpoint, and re-use the existing CuOptServiceSelfHostClient client which is not secure

Additional context
Add any other context, code examples, or references to existing implementations about the feature request here. Internal slack thread: https://nvidia.slack.com/archives/C029C8JHMTL/p1759860849096269

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.