docling-project / docling-project/docling-serve
Multi GPU setup
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.8k
- Forks
- 344
- Avg merge
- 6d 11h
- Merged PRs (30d)
- 8
Description
I deploy docling-serve with multiple gunicorn workers and it crashes on big files because GPU is shared by multiple processes.
docling-core targets a single gpu like `cuda:0`. Is there some way to assign different GPU per worker?
Contributor guide
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 files or tests are named. Start by examining the docling-serve deployment configuration, Gunicorn worker setup, and docling-core device selection; determine whether per-worker GPU assignment is supported. Done means a documented or implemented multi-GPU setup that avoids crashes when processing large files.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- api, backend
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100