fix: MoE concurrency 2→1 (95C thermal emergency)

MoE at 95C with p50=13s latency — thermal throttling causing
death spiral. Both slots stuck processing for 113s p95.
Dense idle at 38C with 2 free slots. Reducing MoE to 1 slot
forces heavy overflow to Dense, giving MoE thermal headroom.

Heavy tier: MoE → Dense → VLM still valid — first heavy goes
to MoE, second overflows to Dense.

router/router.py

@@ -19,7 +19,7 @@ GPU_URLS = {
 }
 # Max concurrent requests per GPU (based on llama.cpp --parallel)
 GPU_MAX_CONCURRENT = {
-    "qwen3.6-35B-A3B": 2,   # 2 slots (Dense-first routing reduces thermal load)
+    "qwen3.6-35B-A3B": 1,   # 1 slot (95C thermal emergency)
     "qwen3.6-27B-code": 2,  # 2 slots (128K context frees VRAM)
     "qwen3.5-9b-vlm": 2,       # 2 slots (12GB VRAM, 4GB headroom)
 }