You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: config/charts/inferencepool/README.md
+25-1Lines changed: 25 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -188,9 +188,33 @@ The following table list the configurable parameters of the chart.
188
188
| `inferenceExtension.monitoring.prometheus.enabled` | Enable Prometheus ServiceMonitor creation for EPP metrics collection. Defaults to `false`. |
189
189
| `inferenceExtension.monitoring.gke.enabled` | Enable GKE monitoring resources (`PodMonitoring` and RBAC). Defaults to `false`. |
190
190
| `inferenceExtension.pluginsCustomConfig` | Custom config that is passed to EPP as inline yaml. |
191
-
| `provider.name` | Name of the Inference Gateway implementation being used. Possible values: `gke`. Defaults to `none`. |
191
+
| `provider.name` | Name of the Inference Gateway implementation being used. Possible values: [`none`, `gke`, or `istio`]. Defaults to `none`. |
192
192
| `provider.gke.autopilot` | Set to `true` if the cluster is a GKE Autopilot cluster. This is only used if `provider.name` is `gke`. Defaults to `false`. |
193
193
194
+
### Provider Specific Configuration
195
+
196
+
This section should document any Gateway provider specific values configurations.
197
+
198
+
#### GKE
199
+
200
+
These are the options available to you with `provider.name` set to `gke`:
| `istio.destinationRule.enabled` | Enable creation of an Istio DestinationRule to configure traffic routing. |
215
+
| `istio.destinationRule.host` | Custom host value for the destination rule. If not set this will use the default value which is derrived from the epp service name and release namespace to gerenate a valid service address. |
216
+
| `istio.destinationRule.trafficPolicy.connectionPool` | Configure the connectionPool level settings of the traffic policy |
217
+
194
218
## Notes
195
219
196
220
This chart will only deploy an InferencePool and its corresponding EndpointPicker extension. Before install the chart, please make sure that the inference extension CRDs are installed in the cluster. For more details, please refer to the [getting started guide](https://gateway-api-inference-extension.sigs.k8s.io/guides/).
0 commit comments