FR: Support for multi-gpu setups
Open
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 132
- Forks
- 17
- PR merge metrics
- No merged PRs in 30d
Description
Hi All,
I have 2 NVIDIA 4060 Ti 16GB each in my local llm rig and an AMD CPU.
I need to set the -g nvidia for my GPUs to be seen however I have to select one of the GPUs to run the tests.
Ollama does support loading a single model on multiple GPUs, could this feature be added ?
Many thanks,
Rafik
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
No files, tests, or entry points are named. Start by investigating how the -g nvidia option currently selects a GPU and review Ollama's multi-GPU model-loading support. Done means a benchmark can use one model across multiple GPUs instead of requiring a single selected GPU.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- ollama, typescript
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100