bump to v0.4.16 and regenerate values schema

Author: meffmadd

charts/llm-d-modelservice/Chart.yaml

@@ -13,7 +13,7 @@ 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: "v0.4.15"
+version: "v0.4.16"
 # 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.

charts/llm-d-modelservice/values.schema.json

@@ -4,7 +4,7 @@
     "properties": {
         "accelerator": {
             "additionalProperties": false,
-            "description": " Supported types: nvidia, intel-i915, intel-xe, intel-gaudi, amd, google, cpu, rebellions-atom",
+            "description": "Global workload kind override. Applied to both decode and prefill unless overridden per-role. Supported: Deployment (default), StatefulSet, LeaderWorkerSet workloadKind: StatefulSet Global accelerator configuration Supported types: nvidia, intel-i915, intel-xe, intel-gaudi, amd, google, cpu, rebellions-atom",
             "properties": {
                 "dra": {
                     "default": false,
@@ -1990,10 +1990,10 @@
             "type": "object"
         },
         "multinode": {
-            "default": false,
-            "description": "When true, a LeaderWorkerSet is used instead of a Deployment",
-            "title": "multinode",
-            "type": "boolean"
+            "default": "false",
+            "description": "When true, a LeaderWorkerSet is used instead of a Deployment for both decode and prefill.",
+            "required": [],
+            "title": "multinode"
         },
         "prefill": {
             "additionalProperties": true,

charts/llm-d-modelservice/values.schema.tmpl.json

@@ -4,7 +4,7 @@
   "properties": {
     "accelerator": {
       "additionalProperties": false,
-      "description": " Supported types: nvidia, intel-i915, intel-xe, intel-gaudi, amd, google, cpu, rebellions-atom",
+      "description": "Global workload kind override. Applied to both decode and prefill unless overridden per-role. Supported: Deployment (default), StatefulSet, LeaderWorkerSet workloadKind: StatefulSet Global accelerator configuration Supported types: nvidia, intel-i915, intel-xe, intel-gaudi, amd, google, cpu, rebellions-atom",
       "properties": {
         "dra": {
           "default": false,
@@ -676,10 +676,10 @@
       "type": "object"
     },
     "multinode": {
-      "default": false,
-      "description": "When true, a LeaderWorkerSet is used instead of a Deployment",
-      "title": "multinode",
-      "type": "boolean"
+      "default": "false",
+      "description": "When true, a LeaderWorkerSet is used instead of a Deployment for both decode and prefill.",
+      "required": [],
+      "title": "multinode"
     },
     "prefill": {
       "additionalProperties": true,

charts/llm-d-modelservice/values.yaml

@@ -83,8 +83,7 @@ modelArtifacts:
   # Set to false for pvc+hf:// when Hugging Face cache writes are needed; other URI schemes ignore this setting.
   readOnly: true
 
-# -- DEPRECATED: Use workloadKind: LeaderWorkerSet instead.
-# When true, a LeaderWorkerSet is used instead of a Deployment for both decode and prefill.
+# -- When true, a LeaderWorkerSet is used instead of a Deployment for both decode and prefill.
 multinode: false
 
 # -- Global workload kind override. Applied to both decode and prefill unless overridden per-role.