Feature Request: Auto-sleep / idle unload for `flm serve`
Open
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 1.9k
- Forks
- 152
- Avg merge
- 4h 14m
- Merged PRs (30d)
- 11
Description
Please, add an option to flm serve that automatically unloads the model from memory after a configurable period of inactivity, and transparently reloads it on the next incoming request.
Same idea and semantics as the recently merged llama.cpp feature: ggml-org/llama.cpp#18228 (--sleep-idle-seconds).
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 at the flm serve entry point and review the linked llama.cpp --sleep-idle-seconds feature for the intended semantics. Implement configurable idle unloading with transparent reload on the next incoming request, then verify that serving resumes correctly after the idle period.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- ai-infra-agents, backend
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 55/100