modelscope / modelscope/DiffSynth-Studio
wan2.2-S2V training always got OOM on H100-80GB GPU
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
tried examples/wanvideo/model_training/full/Wan2.2-S2V-14B.sh but always got OOM whatever how to reduce height/width/num_frames
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the out-of-memory failure with examples/wanvideo/model_training/full/Wan2.2-S2V-14B.sh on an H100-80GB GPU, varying the height, width, and frame settings mentioned in the report. Trace the training configuration to identify why those reductions do not prevent OOM; done means the example can start training within the reported GPU memory limit.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100