Releasev0.1.2 (#345)

kerthcet · web-flow · commit d1faf2cd65a4 · 2025-04-17T16:42:02.000+08:00
* Update chart values

Signed-off-by: kerthcet &lt;kerthcet@gmail.com&gt;

* Revert lws config

Signed-off-by: kerthcet &lt;kerthcet@gmail.com&gt;

* Update config

Signed-off-by: kerthcet &lt;kerthcet@gmail.com&gt;

* Fix prometheus error

Signed-off-by: kerthcet &lt;kerthcet@gmail.com&gt;

* Release v0.1.2

Signed-off-by: kerthcet &lt;kerthcet@gmail.com&gt;

---------

Signed-off-by: kerthcet &lt;kerthcet@gmail.com&gt;
diff --git a/chart/Chart.yaml b/chart/Chart.yaml
@@ -13,9 +13,9 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.0.7
+version: 0.0.8
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
-appVersion: 0.1.1
+appVersion: 0.1.2
diff --git a/chart/crds/playground-crd.yaml b/chart/crds/playground-crd.yaml
@@ -241,6 +241,7 @@ spec:
                       MaxReplicas indicates the maximum number of inference workloads based on the traffic.
                       Default to nil means there's no limit for the instance number.
                     format: int32
+                    minimum: 1
                     type: integer
                   minReplicas:
                     default: 1
@@ -863,6 +864,8 @@ spec:
                             type: array
                         type: object
                     type: object
+                required:
+                - maxReplicas
                 type: object
               modelClaim:
                 description: |-
diff --git a/chart/templates/backends/llamacpp.yaml b/chart/templates/backends/llamacpp.yaml
@@ -1,4 +1,4 @@
-{{- if .Values.backendRuntime.install -}}
+{{- if .Values.backendRuntime.enable -}}
 apiVersion: inference.llmaz.io/v1alpha1
 kind: BackendRuntime
 metadata:
diff --git a/chart/templates/backends/ollama.yaml b/chart/templates/backends/ollama.yaml
@@ -1,4 +1,4 @@
-{{- if .Values.backendRuntime.install -}}
+{{- if .Values.backendRuntime.enable -}}
 apiVersion: inference.llmaz.io/v1alpha1
 kind: BackendRuntime
 metadata:
diff --git a/chart/templates/backends/sglang.yaml b/chart/templates/backends/sglang.yaml
@@ -1,4 +1,4 @@
-{{- if .Values.backendRuntime.install -}}
+{{- if .Values.backendRuntime.enable -}}
 apiVersion: inference.llmaz.io/v1alpha1
 kind: BackendRuntime
 metadata:
diff --git a/chart/templates/backends/tgi.yaml b/chart/templates/backends/tgi.yaml
@@ -1,4 +1,4 @@
-{{- if .Values.backendRuntime.install -}}
+{{- if .Values.backendRuntime.enable -}}
 apiVersion: inference.llmaz.io/v1alpha1
 kind: BackendRuntime
 metadata:
diff --git a/chart/templates/backends/vllm.yaml b/chart/templates/backends/vllm.yaml
@@ -1,4 +1,4 @@
-{{- if .Values.backendRuntime.install -}}
+{{- if .Values.backendRuntime.enable -}}
 apiVersion: inference.llmaz.io/v1alpha1
 kind: BackendRuntime
 metadata:
diff --git a/chart/templates/lws/leaderworkerset.yaml b/chart/templates/lws/leaderworkerset.yaml
@@ -1,4 +1,4 @@
-{{- if .Values.leaderWorkerSet.install -}}
+{{- if .Values.leaderWorkerSet.enable -}}
 apiVersion: v1
 kind: Namespace
 metadata:
@@ -16681,7 +16681,7 @@ spec:
         - --zap-log-level=2
         command:
         - /manager
-        image: {{ .Values.backendRuntime.image.repository }}:{{ .Values.backendRuntime.image.tag }}
+        image: registry.k8s.io/lws/lws:v0.5.0
         livenessProbe:
           httpGet:
             path: /healthz
diff --git a/chart/templates/prometheus/prometheus.yaml b/chart/templates/prometheus/prometheus.yaml
@@ -14,7 +14,7 @@ spec:
     # https://github.com/kubernetes-sigs/jobset/blob/main/config/components/prometheus/monitor.yaml#L7
     matchLabels:
       control-plane: controller-manager
-      {{- include "chart.selectorLabels" . | nindent 4 }}
+    {{- include "chart.selectorLabels" . | nindent 6 }}
   resources:
     requests:
       memory: 400Mi
diff --git a/chart/templates/prometheus/service-monitor.yaml b/chart/templates/prometheus/service-monitor.yaml
@@ -22,6 +22,5 @@ spec:
       insecureSkipVerify: true
   selector:
     matchLabels:
-      control-plane: controller-manager
-      {{- include "chart.selectorLabels" . | nindent 4 }}
+    {{- include "chart.selectorLabels" . | nindent 6 }}
 {{- end }}
diff --git a/chart/values.global.yaml b/chart/values.global.yaml
@@ -1,7 +1,7 @@
 fullnameOverride: "llmaz"
 
 backendRuntime:
-  install: true
+  enable: true
   llamacpp:
     image:
       repository: ghcr.io/ggerganov/llama.cpp
@@ -24,11 +24,8 @@ backendRuntime:
       tag: v0.7.3
 
 leaderWorkerSet:
-  install: true
-  image:
-    repository: registry.k8s.io/lws/lws
-    tag: v0.5.0
+  enable: true
 
 prometheus:
-  # -- Whether to enable Prometheus metrics exporting.
-  enable: false
+  # Prometheus is required to enable smart routing.
+  enable: true
diff --git a/chart/values.yaml b/chart/values.yaml
@@ -12,7 +12,7 @@ controllerManager:
         - ALL
     image:
       repository: inftyai/llmaz
-      tag: main
+      tag: v0.1.2
     resources:
       limits:
         cpu: 500m
diff --git a/config/manager/kustomization.yaml b/config/manager/kustomization.yaml
@@ -5,4 +5,4 @@ kind: Kustomization
 images:
 - name: controller
   newName: inftyai/llmaz
-  newTag: main
+  newTag: v0.1.2
diff --git a/config/prometheus/monitor.yaml b/config/prometheus/monitor.yaml
@@ -20,4 +20,4 @@ spec:
         insecureSkipVerify: true
   selector:
     matchLabels:
-      app.kubernetes.io/name: service
+      app.kubernetes.io/name: llmaz
diff --git a/docs/installation.md b/docs/installation.md
@@ -3,7 +3,8 @@
 ## Prerequisites
 
 - Kubernetes version >= 1.27
-- Helm 3
+- Helm 3, see [installation](https://helm.sh/docs/intro/install/).
+- Prometheus, see [installation](https://github.com/InftyAI/llmaz/tree/main/docs/prometheus-operator#install-the-prometheus-operator).
 
 ## Install a released version
 
diff --git a/index.yaml b/index.yaml
@@ -1,6 +1,16 @@
 apiVersion: v1
 entries:
   llmaz:
+  - apiVersion: v2
+    appVersion: 0.1.2
+    created: "2025-04-17T16:34:28.456285+08:00"
+    description: A Helm chart for llmaz
+    digest: 7b86ddb7338071456ef04a7c8d6b25be697c2e3016096dbb6497688abb9bc414
+    name: llmaz
+    type: application
+    urls:
+    - https://inftyai.github.io/llmaz/llmaz-0.0.8.tgz
+    version: 0.0.8
   - apiVersion: v2
     appVersion: 0.1.1
     created: "2025-02-18T14:46:30.474789+08:00"
@@ -71,4 +81,4 @@ entries:
     urls:
     - https://inftyai.github.io/llmaz/llmaz-0.0.1.tgz
     version: 0.0.1
-generated: "2025-02-18T14:46:30.460221+08:00"
+generated: "2025-04-17T16:34:28.442325+08:00"

Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-{{- if .Values.backendRuntime.install -}}`
	`1`	`+{{- if .Values.backendRuntime.enable -}}`
`2`	`2`	`apiVersion: inference.llmaz.io/v1alpha1`
`3`	`3`	`kind: BackendRuntime`
`4`	`4`	`metadata:`