feat(watchdog): add Memory resource reclaimer #7583
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
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
✅ Deploy Preview for localai ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
mudler commented Dec 15, 2025
| gpus = append(gpus, nvidiaGPUs...) | ||
| } | ||
| | ||
| // XXX: Note - I could not test this with AMD and Intel GPUs, so I'm not sure if it works and it was added with the help of AI. |
Owner Author
There was a problem hiding this comment.
Just for reference ^ I could not really come along with the CLI for specific GPUs because I don't own all of them, however, that was not the goal of this PR. The goal of this PR is to provide all the infrastructure on top of it so we can make use of the GPU data. We can iterate on how we get the GPU data easily later on, as we can move away from this implementation quite easily.
mudler changed the title Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
mudler changed the title | return nil, err | ||
| } | ||
| | ||
| total := uint64(memory.TotalUsableBytes) |
Check failure
Code scanning / gosec
integer overflow conversion uint64 -> int
mudler force-pushed the feat/gpu-resource-eviction branch from bd32e19 to c39a3a2 Compare Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
mudler force-pushed the feat/gpu-resource-eviction branch from c39a3a2 to 5c618a8 Compare 
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 Outdated suggestions cannot be applied.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 is related to #5352
This PR introduces a general Memory reclaimer. We will collect resources from the running system such as GPU ram in use, or just standard RAM usage, and based on that, if exceeds a certain treshold (that can be set explicitly by the user) we start reaping other models (LRU).
This is just a baseline to start, and places basically the foundation to enhance this further in any direction we might want to take it, but should be a good starting point.
Notes for Reviewers
Signed commits