Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions dist/chart/stable.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ controllerManager:
container:
image:
repository: aibrix/controller-manager
tag: v0.5.0-rc.3
tag: v0.5.0
imagePullPolicy: IfNotPresent
resources:
limits:
Expand Down Expand Up @@ -43,7 +43,7 @@ gatewayPlugin:
container:
image:
repository: aibrix/gateway-plugins
tag: v0.5.0-rc.3
tag: v0.5.0
imagePullPolicy: IfNotPresent
resources:
limits:
Expand Down Expand Up @@ -88,7 +88,7 @@ gpuOptimizer:
container:
image:
repository: aibrix/runtime
tag: v0.5.0-rc.3
tag: v0.5.0
resources:
limits:
cpu: 500m
Expand Down Expand Up @@ -143,7 +143,7 @@ metadata:
container:
image:
repository: aibrix/metadata-service
tag: v0.5.0-rc.3
tag: v0.5.0
imagePullPolicy: IfNotPresent
resources:
limits:
Expand Down
2 changes: 1 addition & 1 deletion dist/chart/templates/gateway-instance/gateway.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -155,4 +155,4 @@ spec:
http_header_name: "target-pod"
connect_timeout: {{ .Values.gateway.envoyPatchPolicy.route.connectTimeout }}
lb_policy: CLUSTER_PROVIDED
dns_lookup_family: V4_ONLY
dns_lookup_family: V4_ONLY
19 changes: 19 additions & 0 deletions docs/source/getting_started/installation/installation.rst
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,25 @@ Prerequisites
# Install envoy-gateway, this is not aibrix component. you can also use helm package to install it.
helm install eg oci://docker.io/envoyproxy/gateway-helm --version v1.2.8 -n envoy-gateway-system --create-namespace

# patch the configuration to enable EnvoyPatchPolicy, this is super important!
kubectl apply -f - <<EOF
apiVersion: v1
kind: ConfigMap
metadata:
name: envoy-gateway-config
namespace: envoy-gateway-system
data:
envoy-gateway.yaml: |
apiVersion: gateway.envoyproxy.io/v1alpha1
kind: EnvoyGateway
provider:
type: Kubernetes
gateway:
controllerName: gateway.envoyproxy.io/gatewayclass-controller
extensionApis:
enableEnvoyPatchPolicy: true
EOF
Comment on lines +46 to +63
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

Using kubectl apply to modify a resource managed by Helm can lead to configuration drift and potential issues during chart upgrades, as Helm may not be aware of these manual changes. A more idiomatic and safer approach is to configure envoy-gateway using Helm values during installation.

The envoy-gateway Helm chart likely supports enabling EnvoyPatchPolicy via a value. The installation command could be updated to pass this setting directly. For example:

helm install eg oci://docker.io/envoyproxy/gateway-helm --version v1.2.8 -n envoy-gateway-system --create-namespace \
  --set envoyGateway.extensionApis.enableEnvoyPatchPolicy=true

Please verify the exact value path from the envoy-gateway Helm chart's values.yaml and update the documentation to use the --set flag or a values file. This will make the installation process more robust and align with Helm best practices.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this is not supported yet. envoyproxy/gateway#7458 tracked in this issue


.. note::
If you are experiencing network issues with `docker.io`, you can install the helm chart from the code repo https://github.com/envoyproxy/gateway/tree/main/charts/gateway-helm instead.

Expand Down
2 changes: 1 addition & 1 deletion docs/source/getting_started/quickstart.rst
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ Depending on where you deployed the AIBrix, you can use either of the following
.. code-block:: bash
# list models
curl -v http://${ENDPOINT}/v1/models
curl -v http://${ENDPOINT}/v1/models/
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

You've added a trailing slash to the /v1/models endpoint URL. For consistency, and in case it's needed to avoid redirects, consider adding a trailing slash to the other API endpoint examples in this document as well.

For example:

  • http://${ENDPOINT}/v1/completions should become http://${ENDPOINT}/v1/completions/
  • http://${ENDPOINT}/v1/chat/completions should become http://${ENDPOINT}/v1/chat/completions/

Applying this change consistently across all example curl commands would improve the documentation's clarity and correctness.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

/v1/models/ is a little bit different.

# completion api
curl -v http://${ENDPOINT}/v1/completions \
Expand Down
2 changes: 2 additions & 0 deletions samples/quickstart/model.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -11,10 +11,12 @@ spec:
selector:
matchLabels:
model.aibrix.ai/name: deepseek-r1-distill-llama-8b
model.aibrix.ai/port: "8000"
template:
metadata:
labels:
model.aibrix.ai/name: deepseek-r1-distill-llama-8b
model.aibrix.ai/port: "8000"
spec:
containers:
- command:
Expand Down
2 changes: 1 addition & 1 deletion samples/quickstart/vke/model.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -52,7 +52,7 @@ spec:
value: https://tos-s3-cn-beijing.ivolces.com
- name: TOS_REGION
value: cn-beijing
image: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/runtime:v0.5.0-rc.2
image: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/runtime:v0.5.0
name: init-model
volumeMounts:
- mountPath: /models
Expand Down