VLM migration: qwen3.5-9b-vlm → gemma-4-12b across entire harness

- router/router.py: model ID, context window (131K→262K), VRAM comment
- litellm_config.yaml: model name updated
- gpu-router.conf, gpu-router-docker.conf: pool names, comments
- dashboard/dashboard.py: MODELS array refactor for single-point config
- README.md: architecture diagram, model table

litellm_config.yaml

@@ -11,9 +11,9 @@ model_list:
       api_base: http://192.168.68.8:8080/v1
       api_key: "not-needed"
 
-  - model_name: qwen3.5-9b-vlm
+  - model_name: gemma-4-12b
     litellm_params:
-      model: openai/qwen3.5-9b-vlm
+      model: openai/gemma-4-12b
       api_base: http://192.168.68.110:8080/v1
       api_key: "not-needed"