Router: 300s timeout, gpu_decr bugfix. Dashboard: Bootstrap 5 modern redesign with KPI stats, equal-height cards, queue ring. Nginx: 600s timeout.

router/router.py

@@ -210,7 +210,7 @@ def chat():
             except Exception: pass
         start = time.time()
         resp = requests.post(url+"/chat/completions", json=rd,
-            headers={"Content-Type":"application/json","Authorization":"Bearer not-needed"}, timeout=120, stream=is_stream)
+            headers={"Content-Type":"application/json","Authorization":"Bearer not-needed"}, timeout=300, stream=is_stream)
         lat = int((time.time()-start)*1000)
         gpu_decr(model)  # Release slot
         
@@ -229,8 +229,9 @@ def chat():
         data["routing"] = {"model":model,"reason":reason,"gpu":url,"tier":tier,"agent":agent,"latency_ms":lat,"active_gpu":gpu_active_count(model)}
         bcast()
         return jsonify(data)
-    except requests.Timeout: 
-        gpu_decr(model if 'model' in dir() else "unknown")
+    except requests.Timeout:
+        try: gpu_decr(model)
+        except: pass
         return jsonify({"error":"timeout"}), 504
     except Exception as e:
         log.error("Error: %s\n%s", e, traceback.format_exc())