NVIDIA-NeMo / NVIDIA-NeMo/Automodel

Support for vLLM in 26.04

Open
#1,433 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
Python
Stars
963
Forks
318
Avg merge
3d 20h
Merged PRs (30d)
143

Description

Is your feature request related to a problem? Please describe.
Add vLLM in our docker container to streamline the train-inference workflow.

Describe the solution you'd like
We want to include tests in our Gha CI and the software on the docker container.

Describe alternatives you've considered
A clear and concise description of any alternative solutions or features you've considered.

Additional context
I'm adding @thomasdhc for the automation, but will update assignees on code side.

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 locating the Docker container definition and GitHub Actions CI workflows used by Automodel. Determine how vLLM should be added to the container and which CI tests should cover the train-inference workflow. Done means the container includes vLLM and the relevant tests run successfully in GitHub Actions.

Written by the indexing model from the issue text.

Assessment

Tech stack
docker, github-actions, python
Domain
ci-cd, devops
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.