NVIDIA-NeMo / NVIDIA-NeMo/Gym

question: does ng_run run wait for model endpoint

Open
#673 0 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

Q: does ng_run wait for the policy_base_url to be ready (e.g. an sglang or vllm model)? or will that have to implemented by the client launching ng_run?

A: for external servers it will not wait to be ready.
but you can also try LocalVLLMModel which will wait https://github.com/NVIDIA-NeMo/Gym/blob/main/responses_api_models/local_vllm_model/configs/nano_v3_single_node.yaml

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

Read the issue's question and the linked responses_api_models/local_vllm_model/configs/nano_v3_single_node.yaml configuration, then inspect the ng_run entry point to verify the stated readiness behavior. Done would require a clearly scoped documentation change explaining whether external policy_base_url servers are awaited and how LocalVLLMModel differs.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, backend
Issue type
Documentation
Difficulty
1/5
Estimated time
Under an hour
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.