deploy qwen 3.8

litellm/litellm.yaml

@@ -42,19 +42,11 @@ data:
       # In-cluster models served by llama.cpp (llama-server, Vulkan on the
       # NUCBox APU). The chat template is applied via --jinja; reasoning (when
       # enabled) comes back in `reasoning_content`.
-      - model_name: deepseek-v4-flash-0731
+      - model_name: qwen3.8-27b
         litellm_params:
-          model: openai/deepseek-v4-flash-0731
-          api_base: http://llamacpp-deepseek-v4-flash-0731.llamacpp/v1
+          model: openai/qwen3.8-27b
+          api_base: http://llamacpp-qwen38-27b.llamacpp/v1
           api_key: "sk-no-auth"
-      - model_name: qwen3.6-27b
-        litellm_params:
-          model: openai/qwen3.6-27b
-          api_base: http://llamacpp-qwen36-27b.llamacpp/v1
-          api_key: "sk-no-auth"
-    router_settings:
-      fallbacks:
-        - deepseek-v4-flash-0731: [qwen3.6-27b]
     litellm_settings:
       #set_verbose: True  # Uncomment this if you want to see verbose logs; not recommended in production
       callbacks: ["arize_phoenix"]
@@ -139,4 +131,3 @@ spec:
     - name: http
       port: 80
       targetPort: 4000
-