fix(amd): dashboard token metrics via Lemonade inner llama-server#607
Merged
Lightheartdevs merged 1 commit intomainfrom Mar 24, 2026
Merged
fix(amd): dashboard token metrics via Lemonade inner llama-server#607Lightheartdevs merged 1 commit intomainfrom
Lightheartdevs merged 1 commit intomainfrom
Conversation
Lemonade wraps llama.cpp and doesn't proxy /metrics through its main API port. Pass --metrics --host 0.0.0.0 to the inner llama-server via --llamacpp-args, expose port 8001, and add LLAMA_METRICS_PORT env var to dashboard-api so it queries the inner process directly. Backwards-compatible: LLAMA_METRICS_PORT defaults to the main service port on non-Lemonade setups. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
—and0on AMD/Lemonade/metricsthrough its main port (8080)--metrics --host 0.0.0.0to the inner llama-server via--llamacpp-argsLLAMA_METRICS_PORT=8001tells dashboard-api to query the inner process directlyChanges
docker-compose.amd.yml— added--llamacpp-args,expose: ["8001"],LLAMA_METRICS_PORThelpers.py—metrics_port = int(os.environ.get("LLAMA_METRICS_PORT", port))Backwards compatibility
LLAMA_METRICS_PORTdefaults to the main service port. NVIDIA/CPU setups don't set it — zero change.Test plan
🤖 Generated with Claude Code