Add Ollama Herd - #20
Open
twinsgeeks wants to merge 1 commit into
Open
twinsgeeks wants to merge 1 commit into
twinsgeeks wants to merge 1 commit into
Conversation
Owner
|
@twinsgeeks there seems to be a lot of unrelated changes, can you help to change to add only the relevant change? |
Owner
|
@twinsgeeks thanks for adding this. I saw a lot of unwanted changes. Can you help to update your branch to add only your entry? |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds Ollama Herd under Libraries and Tools.
It treats
mlx_lm.serveras a first-class backend — supervising one subprocess per configured model, merging their models into a fleet view, and routingmlx:prefixed requests to the right one — alongside Ollama on the same endpoint. Nodes are discovered over mDNS, and requests are scored on memory fit, thermal state, queue depth and already-loaded models, which matters on Apple Silicon where a cold load of a large model is expensive.MIT licensed, Python, actively maintained (v0.9.2 released 2026-08-16). Inserted alphabetically to match the section.