aigc-apps / aigc-apps/VideoX-Fun
Wan 14B train problem！
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.3k
- Forks
- 188
- Avg merge
- 2d 22h
- Merged PRs (30d)
- 3
Description
I'm using DeepSpeed ZeRO Stage 3 + bf16 + xFormers + enable_text_encoder_in_dataloader + low_vram, with batch size = 1.
My input video is 81 frames of size 480×832, and I'm doing full fine-tuning.
Even with 8× A800 80GB GPUs, I'm still encountering OOM (Out of Memory) errors.
What could be the reason for this? Any suggestions on how to reduce memory usage further?
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
No file, test, or entry point is named. Start by reproducing the reported Wan 14B full-fine-tuning setup and profiling memory across the listed DeepSpeed, bf16, xFormers, dataloader, resolution, and batch-size settings; done means identifying the OOM cause and documenting a validated way to reduce memory use.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100