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

gpu-router-docker.conf

@@ -13,7 +13,7 @@ upstream llmgpu_pool {
 }
 
 upstream ocu_llm_pool {
-    ## RTX 5070 — qwen3.5-9b-vlm (VLM) — Vision + light tasks
+    ## New Backend — gemma-4-12b (VLM) — Vision + light tasks
     server 192.168.68.110:8080;
 }
 
@@ -36,7 +36,7 @@ map $http_x_syslog_model $gpu_upstream {
     "heavy"          llmgpu_pool;
     "qwen3.5-27B"    llmgpu_pool;
     "light"          ocu_llm_pool;
-    "qwen3.5-9b-vlm"        ocu_llm_pool;
+    "gemma-4-12b"        ocu_llm_pool;
 }
 
 ## Rate limit zone — 10 req/s per IP, burst of 20