microsoft / microsoft/TRELLIS.2

VRAM usage is unstable, peaking at over 63GB+.

Open
#24 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
11.3k
Forks
1.4k
PR merge metrics
No merged PRs in 30d

Description

I launched the service using app.py and performed inference with Gradio's default settings, yet the VRAM usage unexpectedly peaked at over 63GB+.

The image used is:
https://b2bfiles1.gigab2b.cn/image/wkseller/28252/e80df190d17d9fe469b6ea2f8e1e9bef.png?x-cc=20&x-cu=100623&x-ct=1764230400&x-cs=aee8339598781bbc86655d576f09b0f8

Contributor guide

No contributing guide indexed for this repository

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 by reproducing the inference through app.py with Gradio's default settings and the linked image. Measure VRAM throughout the run, then trace the cause of the peak above 63GB and verify that the same workload no longer produces unexpectedly high or unstable usage.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.