Skip to content

Commit

Permalink
minor edits
Browse files Browse the repository at this point in the history
  • Loading branch information
syaseen-rh committed Jun 5, 2024
1 parent 088efc6 commit 37c7452
Showing 1 changed file with 3 additions and 3 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -27,15 +27,15 @@ endif::[]
. Switch to the *Developer* perspective.
. In the left menu, click *Observe*.
ifdef::upstream,self-managed[]
. As described in link:https://access.redhat.com/documentation/en-us/openshift_container_platform/{ocp-latest-version}/html/building_applications/odc-monitoring-project-and-application-metrics-using-developer-perspective#odc-monitoring-your-project-metrics_monitoring-project-and-application-metrics-using-developer-perspective[monitoring project metrics^], use the web console to run queries for `caikit_*`, `tgi_*`, `ovms_*` and `vllm:*` model-serving runtime metrics. You can also run queries for `istio_*` metrics that are related to OpenShift Service Mesh. A few example are listed below:
. As described in link:https://access.redhat.com/documentation/en-us/openshift_container_platform/{ocp-latest-version}/html/building_applications/odc-monitoring-project-and-application-metrics-using-developer-perspective#odc-monitoring-your-project-metrics_monitoring-project-and-application-metrics-using-developer-perspective[monitoring project metrics^], use the web console to run queries for `caikit_*`, `tgi_*`, `ovms_*` and `vllm:*` model-serving runtime metrics. You can also run queries for `istio_*` metrics that are related to OpenShift Service Mesh. You can use the following examples as starting points:
.. The following query displays the number of successful inference requests over a period of time for a model deployed with the vLLM runtime:
+
[source,subs="+quotes"]
----
sum(increase(vllm:request_success_total{namespace='${namespace}',model_name='${model_name}'}[${rate_interval}]))
----

.. The following query dispalys the number of successful inference requests over a period of time for a model deployed with the TGIS runtime:
.. The following query displays the number of successful inference requests over a period of time for a model deployed with the TGIS runtime:
+
[source,subs="+quotes"]
----
Expand All @@ -44,7 +44,7 @@ sum(increase(tgi_request_success{namespace=${namespace}, pod=~'${model_name}-pre

endif::[]
ifdef::cloud-service[]
. As described in link:https://docs.openshift.com/dedicated/observability/monitoring/managing-metrics.html#querying-metrics-for-user-defined-projects-as-a-developer_managing-metrics[Querying metrics for user-defined projects as a developer^] (Red Hat OpenShift Dedicated) or link:https://docs.openshift.com/rosa/observability/monitoring/managing-metrics.html#querying-metrics-for-user-defined-projects-as-a-developer_managing-metrics[Querying metrics for user-defined projects as a developer^] (Red Hat OpenShift Service on AWS), use the web console to run queries for `caikit_*`, `tgi_*`, `ovms_*` and `vllm:*` model-serving runtime metrics. You can also run queries for `istio_*` metrics that are related to OpenShift Service Mesh. A few examples are listed below:
. As described in link:https://docs.openshift.com/dedicated/observability/monitoring/managing-metrics.html#querying-metrics-for-user-defined-projects-as-a-developer_managing-metrics[Querying metrics for user-defined projects as a developer^] (Red Hat OpenShift Dedicated) or link:https://docs.openshift.com/rosa/observability/monitoring/managing-metrics.html#querying-metrics-for-user-defined-projects-as-a-developer_managing-metrics[Querying metrics for user-defined projects as a developer^] (Red Hat OpenShift Service on AWS), use the web console to run queries for `caikit_*`, `tgi_*`, `ovms_*` and `vllm:*` model-serving runtime metrics. You can also run queries for `istio_*` metrics that are related to OpenShift Service Mesh. You can use the following examples as starting points:
.. The following query displays the number of successful inference requests over a period of time for a model deployed with the vLLM runtime:
+
[source,subs="+quotes"]
Expand Down

0 comments on commit 37c7452

Please sign in to comment.