NVIDIA-NeMo / NVIDIA-NeMo/Automodel

feat(speculative): validate multimodal speculative decoding training

Open
#3,167 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

community-request waiting-on-maintainers
Dominant language
Python
Stars
963
Forks
318
Avg merge
3d 20h
Merged PRs (30d)
143

Description

Track remote validation for PR #3166.

Scope:

  • Run the focused MSD unit tests in the server environment.
  • Exercise the VLM target wrapper with a minimal image-conditioned forward.
  • Post the resulting command output and any follow-up findings here.

PR: https://github.com/NVIDIA-NeMo/Automodel/pull/3166

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 reviewing PR #3166 and locating the focused multimodal speculative decoding unit tests and VLM target wrapper it changes. Run the focused tests in the server environment, exercise the minimal image-conditioned forward, and post the command output plus any follow-up findings here.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning, testing-qa
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.