ROCm / ROCm/FastFlowLM

Feature Request: Auto-sleep / idle unload for `flm serve`

Open
#562 0 comments 1 reaction 0 assignees View on GitHub

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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.