Use official vLLM image

stackhpc · Dec 12, 2023 · 50870e0 · 50870e0
1 parent 6876068
commit 50870e0
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 4 deletions.
diff --git a/templates/api/deployment.yml b/templates/api/deployment.yml
@@ -26,12 +26,13 @@ spec:
         - name: data
           mountPath: /root/.cache/huggingface
         command:
-        - python3.11
+        - python3
         args:
           - -m
           - vllm.entrypoints.api_server
           - --model
           - {{ .Values.huggingface.model }}
+          {{- .Values.api.extraArgs | toYaml | nindent 10 }}
         {{- if .Values.huggingface.secretName }}
         envFrom:
         - secretRef:

diff --git a/values.yaml b/values.yaml
@@ -30,7 +30,7 @@ api:
   # Container image config
   image:
     repository: ghcr.io/stackhpc/azimuth-llm-api-base
-    version: fae060a
+    version: "6876068"
   # Service config 
   service:
     name: text-generation-inference
@@ -61,13 +61,15 @@ api:
     rollingUpdate:
       maxSurge: 0%
       maxUnavailable: 100%
-
+  # Extra args to supply to the vLLM backend
+  extraArgs: []
+
 # Configuration for the frontend web interface
 ui:
   # Container image config
   image:
     repository: ghcr.io/stackhpc/azimuth-llm-ui-base
-    version: 7b1d77f
+    version: "6876068"
   # Service config 
   service:
     name: web-app