docs(helm): restore LMCache dashboard explanation in Observability section#982
Merged
ruizhang0101 merged 2 commits intoJun 25, 2026
Merged
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request updates the Helm documentation in helm/README.md to include a new section about the LMCache Dashboard, describing its automatic provisioning and the metrics it displays. Feedback was provided to improve the readability and grammar of the newly added text, specifically suggesting minor phrasing adjustments to make the documentation more natural.
Comment on lines
+462
to
+464
| ### LMCache Dashboard | ||
|
|
||
| If you use the LMCache image in production stack, the chart includes a dedicated LMCache dashboard (provisioned automatically alongside the main vLLM dashboard when `grafanaDashboards.enabled: true`). It contains six fields showing the benefits of CPU offloading: Average time to first token (sec), Cache hit rate (%) in last 1 minute, LMCache retrieve speed (K Tokens / sec), Local CPU cache usage (GB), Number of requested tokens in total, and Number of hit tokens in total. |
Contributor
There was a problem hiding this comment.
The sentence can be improved for better readability and grammatical correctness. Specifically, "in production stack" should be "in the production stack", and "when grafanaDashboards.enabled: true" can be phrased more naturally as "when grafanaDashboards.enabled is set to true".
Suggested change
| ### LMCache Dashboard | |
| If you use the LMCache image in production stack, the chart includes a dedicated LMCache dashboard (provisioned automatically alongside the main vLLM dashboard when `grafanaDashboards.enabled: true`). It contains six fields showing the benefits of CPU offloading: Average time to first token (sec), Cache hit rate (%) in last 1 minute, LMCache retrieve speed (K Tokens / sec), Local CPU cache usage (GB), Number of requested tokens in total, and Number of hit tokens in total. | |
| ### LMCache Dashboard | |
| If you use the LMCache image in the production stack, the chart includes a dedicated LMCache dashboard (provisioned automatically alongside the main vLLM dashboard when `grafanaDashboards.enabled` is set to `true`). It contains six fields showing the benefits of CPU offloading: Average time to first token (sec), Cache hit rate (%) in last 1 minute, LMCache retrieve speed (K Tokens / sec), Local CPU cache usage (GB), Number of requested tokens in total, and Number of hit tokens in total. |
…ction The LMCache dashboard's six fields were documented in the old observability/README.md, which is now deprecated and points readers to helm/README.md#observability for this content. That content never made it over during the helm chart monitoring refactor (vllm-project#860), even though the dashboard itself is still shipped and auto-provisioned via helm/templates/dashboards.yaml. Signed-off-by: Sam <samhoss93@gmail.com>
samhoss93
force-pushed
the
docs/lmcache-dashboard-explanation
branch
from
f336e46 to
a4b997c
Compare
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.
What
Adds back a short explanation of the LMCache dashboard's six fields to
helm/README.md's Observability section.Why
The old
observability/README.mddocumented this under "Import LMCache Dashboard," and is now deprecated with a banner pointing readers tohelm/README.md#observabilityfor the same content. During the monitoring refactor in #860, the dashboard itself (helm/dashboards/lmcache-dashboard.json) moved into the chart and is now auto-provisioned viahelm/templates/dashboards.yaml— a real improvement, no more manualkubectl applystep. But the explanation of what the dashboard actually shows didn't make the move over, so the deprecation banner currently points to a section that doesn't have it.This PR only adds the explanatory text (adapted to note it's auto-provisioned now). It intentionally drops the old manual
kubectl apply/restart commands from the original doc, since those are obsolete now that the chart handles provisioning.Scope
Single doc change, no code/behavior change.