deploy both qwen3.6 versions

litellm/litellm.yaml

@@ -23,13 +23,13 @@ data:
         litellm_params:
           model: "anthropic/claude-sonnet-5"
           api_key: "os.environ/ANTHROPIC_API_KEY"
-      - model_name: gemini-3-flash
+      - model_name: gemini-3.6-flash
         litellm_params:
-          model: gemini/gemini-3-flash-preview
+          model: gemini/gemini-3.6-flash
           api_key: "os.environ/GEMINI_API_KEY"
-      - model_name: tencent/hy3:free
+      - model_name: tencent/hy3
         litellm_params:
-          model: openrouter/tencent/hy3:free
+          model: openrouter/tencent/hy3
           api_key: "os.environ/OPENROUTER_API_KEY"
       - model_name: z-ai/glm-5.2
         litellm_params:
@@ -41,13 +41,20 @@ data:
           api_base: http://10.88.20.12:11434
       # Used by the platform-engineer Hermes agent (deployed in ns platform-engineer).
       # Served by llama.cpp (llama-server, Vulkan on the NUCBox APU) — see
-      # llamacpp/deployment-qwen36.yaml. Thinking is left ON; reasoning comes
-      # back in `reasoning_content` (llama-server --jinja + default reasoning
-      # format). The alias `qwen3.6` is unchanged so Hermes keeps working.
-      - model_name: qwen3.6
+      # llamacpp/deployment-qwen36-27b.yaml. Thinking is left ON; reasoning comes
+      # back in `reasoning_content` (llama-server --jinja + default reasoning format).
+      - model_name: qwen3.6-27b
         litellm_params:
-          model: openai/qwen3.6
-          api_base: http://llamacpp-qwen36.llamacpp/v1
+          model: openai/qwen3.6-27b
+          api_base: http://llamacpp-qwen36-27b.llamacpp/v1
+          api_key: "sk-no-auth"
+      # Faster "flash" variant: Qwen3.6-35B-A3B is a MoE (3B active params), so
+      # inference is much faster than the dense 27B despite more total weights.
+      # See llamacpp/deployment-qwen36-36b-a3b.yaml.
+      - model_name: qwen3.6-36b-a3b
+        litellm_params:
+          model: openai/qwen3.6-36b-a3b
+          api_base: http://llamacpp-qwen36-36b-a3b.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