redeploy qwen3.6 27b

litellm/litellm.yaml

@@ -39,18 +39,19 @@ data:
         litellm_params:
           model: ollama/glm-4.7-flash
           api_base: http://10.88.20.12:11434
-      # In-cluster LLM served by llama.cpp (llama-server, Vulkan on the
-      # NUCBox APU) — see llamacpp/deployment-deepseek-v4-flash-0731.yaml.
-      # DeepSeek-V4-Flash-0731 (UD-IQ1_M, ~87 GiB) is the sole model on the
-      # NUCBox; the two Qwen3.6 models were removed to make VRAM room. The
-      # chat template is applied via llama-server --jinja; reasoning (when
-      # thinking is enabled) comes back in `reasoning_content`. Default
-      # sampling (temp 1.0 / top-p 0.95) is set on the llama-server itself.
+      # 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
         litellm_params:
           model: openai/deepseek-v4-flash-0731
           api_base: http://llamacpp-deepseek-v4-flash-0731.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"
     litellm_settings:
       #set_verbose: True  # Uncomment this if you want to see verbose logs; not recommended in production
       callbacks: ["arize_phoenix"]