ml-explore / ml-explore/mlx-examples
Concurrent requests
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 9k
- Forks
- 1.2k
- PR merge metrics
- No merged PRs in 30d
Description
Can you support better concurrent requests like this?
https://github.com/ollama/ollama/releases/tag/v0.2.0
It would be nice to be able to spread out concurrent requests amongst the RAM/GPU to maintain a good speed, and, to be able to have 30 concurrent requests with a slower speed rather than crashing...
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 reviewing the linked Ollama v0.2.0 release and the MLX examples involved in handling requests; the issue does not name a file, test, or entry point. Clarify how concurrent requests should share RAM and GPU resources, and define the expected behavior when handling 30 requests without crashing.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100