Commit Graph

4 Commits

Author SHA1 Message Date
Ettore Di Giacinto
c844b7ac58 feat: disable force eviction (#7725)
* feat: allow to set forcing backends eviction while requests are in flight

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat: try to make the request sit and retry if eviction couldn't be done

Otherwise calls that in order to pass would need to shutdown other
backends would just fail.

In this way instead we make the request sit and retry eviction until it
succeeds. The thresholds can be configured by the user.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* add tests

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* expose settings to CLI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Update docs

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-12-25 14:26:18 +01:00
Ettore Di Giacinto
b348a99b03 chore: move defaults to constants
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-12-16 17:40:51 +01:00
Ettore Di Giacinto
f3c70a96ba chore(memory-reclaimer): use saner defaults
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-12-16 16:25:09 +01:00
Ettore Di Giacinto
50f9c9a058 feat(watchdog): add Memory resource reclaimer (#7583)
* feat(watchdog): add GPU reclaimer

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Handle vram calculation for unified memory devices

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Support RAM eviction, set watchdog interval from runtime settings

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-12-16 09:15:18 +01:00