Merge pull request #112 from stackhpc/update/vllm-v0.9.1

Update vLLM to v0.9.1

Author: sd109

charts/azimuth-chat/values.schema.json

@@ -40,7 +40,7 @@
                                     "type": "string",
                                     "title": "Backend vLLM version",
                                     "description": "The vLLM version to use as a backend. Must be a version tag from [this list](https://github.com/vllm-project/vllm/tags)",
-                                    "default": "v0.9.0.1"
+                                    "default": "v0.9.1"
                                 }
                             }
                         }

charts/azimuth-image-analysis/values.schema.json

@@ -36,7 +36,7 @@
                                     "type": "string",
                                     "title": "Backend vLLM version",
                                     "description": "The vLLM version to use as a backend. Must be a version tag from [this list](https://github.com/vllm-project/vllm/tags)",
-                                    "default": "v0.9.0.1"
+                                    "default": "v0.9.1"
                                 }
                             }
                         },

charts/azimuth-llm/values.schema.json

@@ -37,7 +37,7 @@
                             "type": "string",
                             "title": "Backend vLLM version",
                             "description": "The vLLM version to use as a backend. Must be a version tag from [this list](https://github.com/vllm-project/vllm/tags)",
-                            "default": "v0.9.0.1"
+                            "default": "v0.9.1"
                         }
                     }
                 }

charts/azimuth-llm/values.yaml

@@ -37,7 +37,7 @@ api:
     # ghcr.io/stackhpc/vllm-xpu when api.gpus > 0 and intelXPUsEnabled is true,
     # or ghcr.io/stackhpc/vllm-cpu when api.gpus == 0
     repository:
-    version: v0.9.0.1
+    version: v0.9.1
   monitoring:
     enabled: true
   # The number of replicas for the backend deployment