feat: disable force eviction #7725
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ight Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
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>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
✅ Deploy Preview for localai ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR changes eviction behavior such as by default we don't evict anymore models which currently are busy with other requests. The PR also provides a flag to disable/enable this behavior, and various handles to configure the behavior.
These changes make eviction logic more robust and configurable both via CLI/environment variables and the web UI, and allow dynamic updates through the API without requiring a restart.
(below copilot summary)
Eviction and LRU Retry Settings Enhancements:
Added new configuration fields to
ApplicationConfigandRuntimeSettingsfor:ForceEvictionWhenBusy).LRUEvictionMaxRetries).LRUEvictionRetryInterval).[1] [2]
Updated CLI flags, environment variables, and startup logic to support the new eviction settings, allowing them to be set at launch.
[1] [2] [3]
Modified runtime settings loading and application logic to:
runtime_settings.json.[1] [2] [3] [4]
Dynamic Update and Watchdog Integration:
[1] [2] [3]
Web UI Improvements:
settings.htmlfor the new eviction settings, including checkboxes and input fields, and ensured these settings are loaded, displayed, and submitted correctly via the frontend.[1] [2] [3] [4]
Notes for Reviewers
Signed commits