routing and dashboard fixes

packages/node/meshnet_node/startup.py

@@ -139,22 +139,33 @@ def _hardware_label(device: str, gpu_name: str | None = None) -> str:
     return "CPU"
 
 
-def _max_assignable_layers(memory_mb: int, total_layers: int | None) -> int:
+def _max_assignable_layers(
+    memory_mb: int,
+    total_layers: int | None,
+    bytes_per_layer: int | None = None,
+) -> int:
     if total_layers is None or total_layers <= 0 or memory_mb <= 0:
         return 0
     budget_bytes = memory_mb * 1024 * 1024
-    return min(total_layers, int((budget_bytes * 0.8) // _DEFAULT_BYTES_PER_LAYER))
+    layer_bytes = bytes_per_layer or _DEFAULT_BYTES_PER_LAYER
+    return min(total_layers, int((budget_bytes * 0.8) // layer_bytes))
 
 
-def _shard_budget_line(memory_mb: int, memory_source: str, total_layers: int | None, quantization: str) -> str:
+def _shard_budget_line(
+    memory_mb: int,
+    memory_source: str,
+    total_layers: int | None,
+    quantization: str,
+    bytes_per_layer: int | None = None,
+) -> str:
     memory_gb = memory_mb / 1024
     gb_str = f"{memory_gb:.1f} GB"
     budget_quantization = "bfloat16" if quantization == "auto" else quantization
     if total_layers is None or total_layers <= 0:
         return f"Memory budget: {gb_str} {memory_source}; shard budget: unknown model layer count"
-    max_layers = _max_assignable_layers(memory_mb, total_layers)
+    max_layers = _max_assignable_layers(memory_mb, total_layers, bytes_per_layer=bytes_per_layer)
     # Remaining capacity after one full model load (rough estimate)
-    shard_bytes = max_layers * _DEFAULT_BYTES_PER_LAYER
+    shard_bytes = max_layers * (bytes_per_layer or _DEFAULT_BYTES_PER_LAYER)
     remaining_gb = (memory_mb * 1024 * 1024 - shard_bytes) / (1024 ** 3)
     remaining_str = f"; {remaining_gb:.1f} GB remaining after full load" if remaining_gb > 1 else ""
     return (
@@ -164,6 +175,23 @@ def _shard_budget_line(memory_mb: int, memory_source: str, total_layers: int | N
     )
 
 
+def _assignment_bytes_per_layer(assignment: dict, quantization: str) -> int | None:
+    bytes_per_layer = assignment.get("bytes_per_layer")
+    if isinstance(bytes_per_layer, int) and bytes_per_layer > 0:
+        return bytes_per_layer
+    if not isinstance(bytes_per_layer, dict):
+        return None
+    keys = [quantization, "bfloat16", "bf16", "int8", "nf4"]
+    for key in keys:
+        value = bytes_per_layer.get(key)
+        if isinstance(value, int) and value > 0:
+            return value
+    for value in bytes_per_layer.values():
+        if isinstance(value, int) and value > 0:
+            return value
+    return None
+
+
 def _post_json(url: str, payload: dict, timeout: float = 10.0) -> dict:
     data = json.dumps(payload).encode()
     req = urllib.request.Request(