thu-ml / thu-ml/TurboDiffusion
4090 - 24G出现 OOM
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.7k
- Forks
- 277
- Avg merge
- 2h 57m
- Merged PRs (30d)
- 2
Description
使用4090显卡进行720p的推理时，报错OOM，使用的torch为2.8.0，这张显卡上我还有一个380MB的显存被其他进程给占用，和这个有关系吗？
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 720p inference on an RTX 4090 with torch 2.8.0 and inspect the attached OOM screenshot. Compare the result with and without the other process using 380 MB of GPU memory. Done means determining whether that memory usage explains the OOM and documenting the confirmed cause or workaround.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100