feat: harden node placement and partial model loading

packages/node/meshnet_node/cli.py

@@ -36,6 +36,12 @@ def _load_env_file(path: Path) -> None:
         os.environ[key] = value
 
 
+def _apply_relay_concurrency_flag(value: int | None) -> None:
+    """Expose relay bridge worker cap via CLI (env MESHNET_RELAY_CONCURRENCY)."""
+    if value is not None:
+        os.environ["MESHNET_RELAY_CONCURRENCY"] = str(max(1, value))
+
+
 def _load_env_defaults() -> None:
     """Load machine-specific, local, and user-level node env defaults."""
     machine = socket.gethostname().strip()
@@ -189,6 +195,8 @@ def _cmd_default(args) -> int:
     if getattr(args, "cpu", False):
         overrides["force_cpu"] = True
 
+    _apply_relay_concurrency_flag(getattr(args, "relay_concurrency", None))
+
     if overrides:
         cfg = merge_cli_overrides(cfg, **overrides)
 
@@ -349,6 +357,8 @@ def _cmd_start(args) -> int:
     if getattr(args, "node_name", None):
         cfg["node_name"] = args.node_name
 
+    _apply_relay_concurrency_flag(getattr(args, "relay_concurrency", None))
+
     # Legacy start: just run without the dashboard (keep original blocking loop)
     from .startup import run_startup
 
@@ -433,6 +443,8 @@ def main() -> None:
                         help="Set PyTorch inter-op CPU worker threads")
     parser.add_argument("--cpu", action="store_true",
                         help="Force CPU inference even when a GPU is available")
+    parser.add_argument("--relay-concurrency", type=int, metavar="N",
+                        help="Max concurrent relay-http-request workers (env MESHNET_RELAY_CONCURRENCY)")
     parser.add_argument("--debug", action="store_true", help="Enable verbose node debug logging")
     parser.add_argument("--no-tui", action="store_true", help="Plain-text output (no rich dashboard)")
     parser.add_argument("--compact", action="store_true", help="Single-line status output")
@@ -510,6 +522,8 @@ def main() -> None:
                            help="Set PyTorch inter-op CPU worker threads")
     start_cmd.add_argument("--cpu", action="store_true",
                            help="Force CPU inference even when a GPU is available")
+    start_cmd.add_argument("--relay-concurrency", type=int, metavar="N",
+                           help="Max concurrent relay-http-request workers (env MESHNET_RELAY_CONCURRENCY)")
     start_cmd.add_argument("--debug", action="store_true", help="Enable verbose node debug logging")
     start_cmd.add_argument("--tracker-source-disabled", action="store_true",
                            help="Skip tracker/peer model-file sources and download from HuggingFace directly")

packages/node/meshnet_node/model_backend.py

@@ -899,12 +899,41 @@ def _load_partial_model_from_snapshot(
                     dtype=dtype,
                 )
 
-    for module in _active_modules_for_shard(model, shard_start, shard_end):
-        if hasattr(module, "to"):
-            module.to(device)
+    _finalize_active_shard_modules_on_device(model, shard_start, shard_end, device)
     return model
 
 
+def _finalize_active_shard_modules_on_device(
+    model: Any, shard_start: int, shard_end: int, device: Any
+) -> None:
+    """Place active shard modules on device without copying unmaterialized meta weights."""
+    for module in _active_modules_for_shard(model, shard_start, shard_end):
+        parameters = getattr(module, "parameters", None)
+        if not callable(parameters):
+            if hasattr(module, "to"):
+                module.to(device)
+            continue
+        params = list(parameters(recurse=True))
+        buffers_fn = getattr(module, "buffers", None)
+        buffers = list(buffers_fn(recurse=True)) if callable(buffers_fn) else []
+        tensors = params + buffers
+        if not tensors:
+            if hasattr(module, "to"):
+                module.to(device)
+            continue
+        if all(tensor.device.type == "meta" for tensor in tensors):
+            to_empty = getattr(module, "to_empty", None)
+            if callable(to_empty):
+                to_empty(device)
+            continue
+        if all(tensor.device.type != "meta" for tensor in tensors):
+            if hasattr(module, "to"):
+                module.to(device)
+            continue
+        # Partially materialized: set_module_tensor_to_device already placed loaded
+        # weights on the target device; leave remaining meta parameters untouched.
+
+
 def _model_load_plan(
     auto_config: Any,
     model_id: str,