fix(agent): read contextSize from InferenceService CRD#160
Merged
Conversation
The Metal Agent was hardcoding ContextSize to 2048 when starting llama-server processes, ignoring the contextSize field in the InferenceService spec. This caused context overflow errors for prompts exceeding 2048 tokens. Now reads contextSize from isvc.Spec.ContextSize and falls back to 2048 only if not specified in the CRD. Fixes #159 Signed-off-by: Christopher Maher <chris@mahercode.io>
4b185f9 to
c37a63c
Compare
Merged
Closed
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
contextSizefrom the InferenceService CRD spec instead of hardcoding 2048Fixes #159
Test plan
contextSize: 8192and verify llama-server starts with-c 8192contextSizeset and verify fallback to 2048