Merge pull request #1 from sauagarwa/main

Adjusted resource parameters of Model

Author: dminnear-rh

overrides/values-cpu.yaml

@@ -8,18 +8,20 @@ global:
       enabled: true
       resources:
         limits:
-          cpu: "4"
-          memory: 32Gi
+          cpu: "6"
+          memory: 48Gi
         requests:
-          cpu: "1"
-          memory: 16Gi
+          cpu: "2"
+          memory: 24Gi
       args:
         - --enable-auto-tool-choice
         - --chat-template
         - /chat-templates/tool_chat_template_llama3.2_json.jinja
         - --tool-call-parser
         - llama3_json
+        - --dtype
+        - auto
         - --max-model-len
-        - "8192"
+        - "16384"
         - --max-num-seqs
-        - "2"
+        - "1"