THUDM / THUDM/slime

[MultiModal] Current Megatron-Bridge Does Not Support Video Modal

Open
#1,583 2 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
8.5k
Forks
1.3k
Avg merge
5h 36m
Merged PRs (30d)
22

Description

Description

Current docker built from https://github.com/fzyzcjy/Megatron-Bridge/tree/dev_rl (0.3.0.rc0) does not support video pad input, which occurs:

  File "/usr/local/lib/python3.12/dist-packages/megatron/bridge/models/qwen_vl/modelling_qwen3_vl/model.py", line 211, in forward
    assert pixel_values_videos is None and video_grid_thw is None, "not support video now"

Solution

Upgrade to latest 0.4.0.rc0 fix this. Will solve this by a PR later

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 with the Docker image built from the dev_rl branch and check how it pins Megatron-Bridge 0.3.0.rc0. Reproduce the video pad input failure at megatron/bridge/models/qwen_vl/modelling_qwen3_vl/model.py, then verify that the image uses 0.4.0.rc0 and no longer raises the reported video-support assertion.

Written by the indexing model from the issue text.

Assessment

Tech stack
docker, python
Domain
machine-learning
Issue type
Bug
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.