Skip to content

Conversation

@mudler
Copy link
Owner

@mudler mudler commented Dec 12, 2025

This changeset introduces LRU management of loaded backends. Users can set now a maximum number of models to be loaded concurrently, and, when setting LocalAI in single active backend mode we set LRU to 1 for backward compatibility.

Fixes #6068
Related to #5352

This changeset introduces LRU management of loaded backends. Users can
set now a maximum number of models to be loaded concurrently, and, when
setting LocalAI in single active backend mode we set LRU to 1 for
backward compatibility.

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

netlify bot commented Dec 12, 2025

Deploy Preview for localai ready!

Name Link
🔨 Latest commit ea5784d
🔍 Latest deploy log https://app.netlify.com/projects/localai/deploys/693be8e5023a4f0008be3583
😎 Deploy Preview https://deploy-preview-7535--localai.netlify.app
📱 Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify project configuration.

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>
@mudler mudler changed the title feat(loader): refactor single active backend support to LRU feat(loader): refactor single active backend support to LRU eviction Dec 12, 2025
@mudler mudler changed the title feat(loader): refactor single active backend support to LRU eviction feat(loader): enhance single active backend to support LRU eviction Dec 12, 2025
@mudler mudler merged commit fc5b9eb into master Dec 12, 2025
34 checks passed
@mudler mudler deleted the feat/lru branch December 12, 2025 11:28
@mudler mudler added the enhancement New feature or request label Dec 24, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Unload LRU models automatically

2 participants