docs: fleet topology update — PP split renamed frank-default-large, NPU endpoint promoted to frank-default-small, 4-model NPU bakeoff matrix (2026-08-16)

docs/index.md

@@ -8,24 +8,28 @@ Documentation for running vLLM inference on two local machines.
 graph LR
     subgraph Dankserver[NVIDIA Dankserver - Ubuntu 24.04]
         A[RTX 3090 24GB + 62GB RAM]
-        B[llama.cpp ngram-mod
-frank-default-small]
-        C[Qwen3.6-35B-A3B uncensored Q6_K_P
-MoE experts on CPU, port 7770]
-        A --> B --> C
+        B[ggml-rpc worker
+frank-pp-worker, port 50052]
+        A --> B
     end
 
     subgraph Dankclaw[AMD Strix Halo - Ubuntu 26.04]
         D[gfx1151 APU 30GiB phys / 96GiB GPU-visible]
-        E[llama.cpp --spec-default ngram-mod
-frank-default-large]
+        E[llama.cpp PP head
+frank-default-large, port 7770]
         F[Qwen3.8-27B UD-Q8_K_XL
-Vulkan0 backend, port 7770, PARALLEL=2]
+split 0.40/0.60 to worker, MTP+ngram-mod]
         D --> E --> F
+        G[FastFlowLM NPU XDNA2 50 TOPS
+frank-default-small, port 52625]
+        H[gemma4-it:e4b
+12.2 t/s, 32k ctx, vision]
+        D --> G --> H
     end
 
-    G[LLM Clients / API] -->|HTTP :7770| B
-    G -->|HTTP :7770| E
+    I[LLM Clients / API] -->|HTTP :7770| E
+    I -->|HTTP :52625| G
+    E -->|RPC layers 0.40| B
 ```
 
 ## Servers