NVIDIA-NeMo / NVIDIA-NeMo/Gym

Validate GPT-OSS OpenAI model workflow across different endpoints

Open
#217 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

models
Dominant language
Python
Stars
1.2k
Forks
349
Avg merge
1d 21h
Merged PRs (30d)
318

Description

Use cases, pain points, and background
We tried using the GPT-OSS endpoints from build.nvidia.com or inference.nvidia.com and got some errors.

Description:
Try them out and fix them

Design:

Out of scope:

Acceptance Criteria:

  • Obtain build.nvidia.com API key and inference.nvidia.com API key
  • Try out the above flow
  • Fix any issues on Gym infra or try to have a reasonably robust patch for the *.nvidia.com endpoints
  • Write a tutorial on how to get an API key from these places and how to use them

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 obtaining API keys for build.nvidia.com and inference.nvidia.com, then exercise the GPT-OSS workflow across both endpoints to reproduce the reported errors. Trace failures through the Gym infrastructure and verify that the workflow works robustly; done also requires a tutorial explaining API-key acquisition and usage.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
api, documentation
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.