updating to match everything in my homelab.

diagrams/kuberay-unified-backend.mmd

@@ -0,0 +1,77 @@
+```plaintext
+%% KubeRay Unified GPU Backend (ADR-0011)
+%% C4 Component diagram showing RayService endpoints and GPU allocation
+
+flowchart TB
+    subgraph clients["🔌 Clients"]
+        chat["Chat Handler"]
+        voice["Voice Handler"]
+    end
+
+    subgraph rayservice["⚡ KubeRay RayService"]
+        endpoint["ai-inference-serve-svc:8000"]
+        
+        subgraph deployments["Ray Serve Deployments"]
+            direction TB
+            
+            subgraph strixhalo["🟢 khelben (Strix Halo 64GB)"]
+                llm["/llm<br/>vLLM 70B<br/>0.95 GPU"]
+            end
+
+            subgraph rtx2070["🟡 elminster (RTX 2070 8GB)"]
+                whisper["/whisper<br/>Whisper v3<br/>0.5 GPU"]
+                tts["/tts<br/>XTTS<br/>0.5 GPU"]
+            end
+
+            subgraph radeon680m["🔴 drizzt (Radeon 680M 12GB)"]
+                embeddings["/embeddings<br/>BGE-Large<br/>0.8 GPU"]
+            end
+
+            subgraph intelarc["🔵 danilo (Intel Arc)"]
+                reranker["/reranker<br/>BGE-Reranker<br/>0.8 GPU"]
+            end
+        end
+    end
+
+    subgraph kserve["🎯 KServe Compatibility Layer"]
+        direction TB
+        svc1["whisper-predictor.ai-ml"]
+        svc2["tts-predictor.ai-ml"]
+        svc3["llm-predictor.ai-ml"]
+        svc4["embeddings-predictor.ai-ml"]
+        svc5["reranker-predictor.ai-ml"]
+    end
+
+    %% Client connections
+    chat --> endpoint
+    voice --> endpoint
+
+    %% Path routing
+    endpoint --> llm
+    endpoint --> whisper
+    endpoint --> tts
+    endpoint --> embeddings
+    endpoint --> reranker
+
+    %% KServe aliases
+    svc1 -->|"ExternalName"| endpoint
+    svc2 -->|"ExternalName"| endpoint
+    svc3 -->|"ExternalName"| endpoint
+    svc4 -->|"ExternalName"| endpoint
+    svc5 -->|"ExternalName"| endpoint
+
+    classDef client fill:#3498db,color:white
+    classDef endpoint fill:#9b59b6,color:white
+    classDef amd fill:#ED1C24,color:white
+    classDef nvidia fill:#76B900,color:white
+    classDef intel fill:#0071C5,color:white
+    classDef kserve fill:#f39c12,color:black
+
+    class chat,voice client
+    class endpoint endpoint
+    class llm,embeddings amd
+    class whisper,tts nvidia
+    class reranker intel
+    class svc1,svc2,svc3,svc4,svc5 kserve
+
+```