RosettaCommons / RosettaCommons/foundry
[QUEST]multiple GPUs
Open
Nobody has claimed this yet.
question
- Dominant language
- Python
- Stars
- 966
- Forks
- 181
- Avg merge
- 4d 4h
- Merged PRs (30d)
- 2
Description
When using a structure as input, the system reports insufficient GPU memory. For the RFDiffusion3 model, which parts of the code should be modified to distribute the model across multiple GPUs? In other words, what is the specific code implementation that enables multi‑GPU parallel execution for this model? Thank you!
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
Start by tracing how structure inputs reach the RFDiffusion3 model and where GPU memory is allocated. Determine which model components and execution path would need multi-GPU support, then define how successful execution without the reported insufficient-memory failure would be verified.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- distributed-systems, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100