michaelfeil / michaelfeil/infinity
unloading model after some timeout automatically and load the model again after first API inference call
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.9k
- Forks
- 206
- PR merge metrics
- No merged PRs in 30d
Description
### Feature request
unloading model after some timeout automatically and load the model again after first API inference call
When GPU memory is not enough for inference, push requests into a queue and wait for GPU memory
Related but different from #151
### Motivation
this would allow infinity to share GPU with other containers
### Your contribution
testing, i am just learning to code
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
The issue names no files, tests, or entry points. Start by mapping the existing model-loading and API inference request flow, then identify how GPU-memory failures and request queuing are handled. Done means models unload after the configured timeout, reload on the first API inference call, and queued requests wait for available GPU memory.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, api, backend, performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100