From a4b997c961356ad60f6ad46520c735a2a67476a4 Mon Sep 17 00:00:00 2001 From: Sam Date: Tue, 23 Jun 2026 22:43:47 -0400 Subject: [PATCH] docs(helm): restore LMCache dashboard explanation in Observability section 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 (#860), even though the dashboard itself is still shipped and auto-provisioned via helm/templates/dashboards.yaml. Signed-off-by: Sam --- helm/README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/helm/README.md b/helm/README.md index c5ab301a0..0053f7f4a 100644 --- a/helm/README.md +++ b/helm/README.md @@ -459,6 +459,10 @@ kubectl port-forward svc/-grafana 8080:80 Open the webpage at `http://:8080` to access the Grafana web page. The default user name is `admin` and the password can be configured in the values (default is generated by helm and stored in a secret `-grafana`). +### 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. + ### Use Prometheus Adapter to export vLLM metrics The vLLM router can export metrics to Prometheus using the [Prometheus Adapter](https://github.com/prometheus-community/helm-charts/tree/main/charts/prometheus-adapter).