-cpu flag

packages/node/meshnet_node/torch_server.py

@@ -1087,6 +1087,7 @@ class TorchNodeServer:
         cache_dir: Path | None = None,
         debug: bool = False,
         max_loaded_shards: int = 1,
+        force_cpu: bool = False,
     ) -> None:
         self._host = host
         self._requested_port = port
@@ -1097,6 +1098,7 @@ class TorchNodeServer:
             shard_end,
             quantization,
             cache_dir,
+            force_cpu=force_cpu,
         )
         self._backends: dict[str, TorchModelShard] = {self._backend.model_id: self._backend}
         # Auto-detect tracker mode: enabled when shard_start == 0 or explicitly set
@@ -1245,12 +1247,15 @@ def _load_backend(
     shard_end: int,
     quantization: str,
     cache_dir: Path | None = None,
+    force_cpu: bool = False,
 ) -> TorchModelShard:
     from .model_backend import load_torch_shard
 
     quant = validate_quantization(quantization)
     try:
-        return load_torch_shard(model_id, shard_start, shard_end, quant, cache_dir)
+        return load_torch_shard(
+            model_id, shard_start, shard_end, quant, cache_dir, force_cpu=force_cpu
+        )
     except MissingModelDependencyError:
         raise
     except InsufficientVRAMError as exc: