add image repo for lws and all backend runtime, like llama.cpp (#328)

Author: pacoxu

Diff for: chart/templates/backends/llamacpp.yaml

@@ -10,8 +10,8 @@ metadata:
 spec:
   command:
     - ./llama-server
-  image: ghcr.io/ggerganov/llama.cpp
-  version: server
+  image: {{ .Values.backendRuntime.llamacpp.image.repository }}
+  version: {{ .Values.backendRuntime.llamacpp.image.tag }}
   # Do not edit the preset argument name unless you know what you're doing.
   # Free to add more arguments with your requirements.
   recommendedConfigs:

Diff for: chart/templates/backends/ollama.yaml

@@ -11,8 +11,8 @@ spec:
   command:
     - sh
     - -c
-  image: ollama/ollama
-  version: latest
+  image: {{ .Values.backendRuntime.ollama.image.repository }}
+  version: {{ .Values.backendRuntime.ollama.image.tag }}
   envs:
     - name: OLLAMA_HOST
       value: 0.0.0.0:8080

Diff for: chart/templates/backends/sglang.yaml

@@ -12,8 +12,8 @@ spec:
     - python3
     - -m
     - sglang.launch_server
-  image: lmsysorg/sglang
-  version: v0.2.10-cu121
+  image: {{ .Values.backendRuntime.sglang.image.repository }}
+  version: {{ .Values.backendRuntime.sglang.image.tag }}
   # Do not edit the preset argument name unless you know what you're doing.
   # Free to add more arguments with your requirements.
   recommendedConfigs:

Diff for: chart/templates/backends/tgi.yaml

@@ -8,8 +8,8 @@ metadata:
     app.kubernetes.io/created-by: llmaz
   name: tgi
 spec:
-  image: ghcr.io/huggingface/text-generation-inference
-  version: 2.3.1
+  image: {{ .Values.backendRuntime.tgi.image.repository }}
+  version: {{ .Values.backendRuntime.tgi.image.tag }}
   # Do not edit the preset argument name unless you know what you're doing.
   # Free to add more arguments with your requirements.
   recommendedConfigs:

Diff for: chart/templates/backends/vllm.yaml

@@ -12,8 +12,8 @@ spec:
     - python3
     - -m
     - vllm.entrypoints.openai.api_server
-  image: vllm/vllm-openai
-  version: v0.7.3
+  image: {{ .Values.backendRuntime.vllm.image.repository }}
+  version: {{ .Values.backendRuntime.vllm.image.tag }}
   lifecycle:
     preStop:
       exec:

Diff for: chart/templates/lws/leaderworkerset.yaml

@@ -16681,7 +16681,7 @@ spec:
         - --zap-log-level=2
         command:
         - /manager
-        image: registry.k8s.io/lws/lws:v0.5.0
+        image: {{ .Values.backendRuntime.image.repository }}:{{ .Values.backendRuntime.image.tag }}
         livenessProbe:
           httpGet:
             path: /healthz

Diff for: chart/values.global.yaml

@@ -2,6 +2,29 @@ fullnameOverride: "llmaz"
 
 backendRuntime:
   install: true
+  llamacpp:
+    image:
+      repository: ghcr.io/ggerganov/llama.cpp
+      tag: server
+  ollama:
+    image:
+      repository: ollama/ollama
+      tag: latest
+  sglang:
+    image:
+      repository: lmsysorg/sglang
+      tag: v0.2.10-cu121
+  tgi:
+    image:
+      repository: ghcr.io/huggingface/text-generation-inference
+      tag: 2.3.1
+  vllm:
+    image:
+      repository: vllm/vllm-openai
+      tag: v0.7.3
 
 leaderWorkerSet:
   install: true
+  image:
+    repository: registry.k8s.io/lws/lws
+    tag: v0.5.0