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
This commit adds support for the control plane to watch InferencePools. A feature flag has been added to enable/disable processing these resources. By default, it is disabled.
When an HTTPRoute references an InferencePool, we will create a headless Service associated with that InferencePool, and reference it internally in the graph config for that Route. This allows us to use all of our existing logic to get the endpoints and build the proper nginx config for those endpoints.
In a future commit, the nginx config will be updated to handle the proper load balancing for the AI workloads, but for now we just use our default methods by proxy_passing to the upstream.
Copy file name to clipboardExpand all lines: charts/nginx-gateway-fabric/README.md
+2-1Lines changed: 2 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -245,7 +245,7 @@ The following table lists the configurable parameters of the NGINX Gateway Fabri
245
245
|`nginx.usage.resolver`| The nameserver used to resolve the NGINX Plus usage reporting endpoint. Used with NGINX Instance Manager. | string |`""`|
246
246
|`nginx.usage.secretName`| The name of the Secret containing the JWT for NGINX Plus usage reporting. Must exist in the same namespace that the NGINX Gateway Fabric control plane is running in (default namespace: nginx-gateway). | string |`"nplus-license"`|
247
247
|`nginx.usage.skipVerify`| Disable client verification of the NGINX Plus usage reporting server certificate. | bool |`false`|
248
-
| `nginxGateway` | The nginxGateway section contains configuration for the NGINX Gateway Fabric control plane deployment. | object | `{"affinity":{},"autoscaling":{"enable":false},"config":{"logging":{"level":"info"}},"configAnnotations":{},"extraVolumeMounts":[],"extraVolumes":[],"gatewayClassAnnotations":{},"gatewayClassName":"nginx","gatewayControllerName":"gateway.nginx.org/nginx-gateway-controller","gwAPIExperimentalFeatures":{"enable":false},"image":{"pullPolicy":"Always","repository":"ghcr.io/nginx/nginx-gateway-fabric","tag":"edge"},"kind":"deployment","labels":{},"leaderElection":{"enable":true,"lockName":""},"lifecycle":{},"metrics":{"enable":true,"port":9113,"secure":false},"name":"","nodeSelector":{},"podAnnotations":{},"productTelemetry":{"enable":true},"readinessProbe":{"enable":true,"initialDelaySeconds":3,"port":8081},"replicas":1,"resources":{},"service":{"annotations":{},"labels":{}},"serviceAccount":{"annotations":{},"imagePullSecret":"","imagePullSecrets":[],"name":""},"snippetsFilters":{"enable":false},"terminationGracePeriodSeconds":30,"tolerations":[],"topologySpreadConstraints":[]}` |
248
+
| `nginxGateway` | The nginxGateway section contains configuration for the NGINX Gateway Fabric control plane deployment. | object | `{"affinity":{},"autoscaling":{"enable":false},"config":{"logging":{"level":"info"}},"configAnnotations":{},"extraVolumeMounts":[],"extraVolumes":[],"gatewayClassAnnotations":{},"gatewayClassName":"nginx","gatewayControllerName":"gateway.nginx.org/nginx-gateway-controller","gwAPIExperimentalFeatures":{"enable":false},"gwAPIInferenceExtension":{"enable":false},"image":{"pullPolicy":"Always","repository":"ghcr.io/nginx/nginx-gateway-fabric","tag":"edge"},"kind":"deployment","labels":{},"leaderElection":{"enable":true,"lockName":""},"lifecycle":{},"metrics":{"enable":true,"port":9113,"secure":false},"name":"","nodeSelector":{},"podAnnotations":{},"productTelemetry":{"enable":true},"readinessProbe":{"enable":true,"initialDelaySeconds":3,"port":8081},"replicas":1,"resources":{},"service":{"annotations":{},"labels":{}},"serviceAccount":{"annotations":{},"imagePullSecret":"","imagePullSecrets":[],"name":""},"snippetsFilters":{"enable":false},"terminationGracePeriodSeconds":30,"tolerations":[],"topologySpreadConstraints":[]}` |
249
249
|`nginxGateway.affinity`| The affinity of the NGINX Gateway Fabric control plane pod. | object |`{}`|
250
250
|`nginxGateway.autoscaling`| Autoscaling configuration for the NGINX Gateway Fabric control plane. | object |`{"enable":false}`|
251
251
|`nginxGateway.autoscaling.enable`| Enable or disable Horizontal Pod Autoscaler for the control plane. | bool |`false`|
@@ -257,6 +257,7 @@ The following table lists the configurable parameters of the NGINX Gateway Fabri
257
257
|`nginxGateway.gatewayClassName`| The name of the GatewayClass that will be created as part of this release. Every NGINX Gateway Fabric must have a unique corresponding GatewayClass resource. NGINX Gateway Fabric only processes resources that belong to its class - i.e. have the "gatewayClassName" field resource equal to the class. | string |`"nginx"`|
258
258
|`nginxGateway.gatewayControllerName`| The name of the Gateway controller. The controller name must be of the form: DOMAIN/PATH. The controller's domain is gateway.nginx.org. | string |`"gateway.nginx.org/nginx-gateway-controller"`|
259
259
|`nginxGateway.gwAPIExperimentalFeatures.enable`| Enable the experimental features of Gateway API which are supported by NGINX Gateway Fabric. Requires the Gateway APIs installed from the experimental channel. | bool |`false`|
260
+
|`nginxGateway.gwAPIInferenceExtension.enable`| Enable Gateway API Inference Extension support. Allows for configuring InferencePools to route traffic to AI workloads. | bool |`false`|
260
261
|`nginxGateway.image`| The image configuration for the NGINX Gateway Fabric control plane. | object |`{"pullPolicy":"Always","repository":"ghcr.io/nginx/nginx-gateway-fabric","tag":"edge"}`|
261
262
|`nginxGateway.image.repository`| The NGINX Gateway Fabric image to use | string |`"ghcr.io/nginx/nginx-gateway-fabric"`|
262
263
|`nginxGateway.kind`| The kind of the NGINX Gateway Fabric installation - currently, only deployment is supported. | string |`"deployment"`|
0 commit comments