microsoft / microsoft/TRELLIS

Asking for a tremendous amount of VRAM (windows)

Open
#79 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13.7k
Forks
1.3k
PR merge metrics
No merged PRs in 30d

Description

I don't understand, with the example.py, I stumble upon this error:

File "C:\Users\sylle\.conda\envs\trellis\lib\site-packages\diffoctreerast\octree_trivec_rasterizer.py", line 105, in forward
    num_rendered, color, depth, alpha, percent_depth, geomBuffer, binningBuffer, imgBuffer = _C.rasterize_octree_trivecs(*args)
RuntimeError: CUDA out of memory. Tried to allocate 196.89 GiB. GPU 0 has a total capacity of 24.00 GiB of which 16.91 GiB is free.

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

The report names example.py and the failure in diffoctreerast/octree_trivec_rasterizer.py on Windows. Start by reproducing example.py in the reported conda environment and inspect the rasterizer call in the traceback. Done means identifying why the allocation exceeds available VRAM and documenting or fixing the cause.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-graphics
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.