microsoft / microsoft/TRELLIS.2
[Question] low_vram hardware requirement + OOM on A100 80GB when low_vram is disabled
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 11.3k
- Forks
- 1.4k
- PR merge metrics
- No merged PRs in 30d
Description
Hi @JeffreyXiang ,
When I disable low_vram and run the repo's example.py, I still hit CUDA out of memory on an NVIDIA A100 80GB. Is this expected (e.g., due to default resolution/texture/export steps), or does it indicate an abnormal memory peak/leak?
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 with example.py and reproduce the run with low_vram disabled on an NVIDIA A100 80GB. Check memory behavior around the default resolution, texture, and export steps mentioned in the report. Done means determining whether the OOM is expected or identifying evidence of an abnormal memory peak or leak.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-graphics, machine-learning, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100