-cpu flag

packages/node/meshnet_node/startup.py

@@ -15,7 +15,7 @@ from pathlib import Path
 from typing import Any
 
 from .downloader import compute_shard_checksum, download_shard
-from .hardware import detect_hardware, benchmark_throughput_checked
+from .hardware import detect_hardware, benchmark_throughput_checked, with_forced_cpu
 from .model_catalog import model_metadata_for
 from .relay_bridge import RelayHttpBridge, peer_id_from_wallet
 from .server import StubNodeServer
@@ -640,6 +640,7 @@ def run_startup(
     torch_threads: int | None = None,
     torch_interop_threads: int | None = None,
     node_name: str | None = None,
+    force_cpu: bool = False,
 ) -> StubNodeServer | TorchNodeServer:
     """Execute the full startup sequence and return a running node server.
 
@@ -681,6 +682,8 @@ def run_startup(
 
     print("Detecting hardware...", flush=True)
     hw = detect_hardware()
+    if force_cpu:
+        hw = with_forced_cpu(hw)
     torch_thread_config = _configure_torch_threads(torch_threads, torch_interop_threads)
     if torch_thread_config:
         hw.update(torch_thread_config)
@@ -697,6 +700,16 @@ def run_startup(
         vram_mb = vram_mb_override
         shared_vram_mb = 0
         print(f"  Memory budget overridden to {vram_mb / 1024:.1f} GB via --memory", flush=True)
+    elif force_cpu:
+        if gpu_name and vram_mb > 0:
+            print(
+                f"  --cpu: ignoring {gpu_name} "
+                f"({vram_mb / 1024:.1f} GB VRAM); running in CPU mode "
+                f"({ram_mb / 1024:.1f} GB RAM)",
+                flush=True,
+            )
+        else:
+            print(f"  --cpu: running in CPU mode ({ram_mb / 1024:.1f} GB RAM)", flush=True)
     elif device == "cpu":
         gpu_suffix = ""
         if gpu_name and vram_mb > 0:
@@ -718,7 +731,7 @@ def run_startup(
     print(f"  Memory budget: {memory_budget_mb / 1024:.1f} GB {memory_budget_source}", flush=True)
 
     print("Benchmarking compute...", flush=True)
-    if device != "cuda" and gpu_name:
+    if device != "cuda" and gpu_name and not force_cpu:
         _cuda_score, cuda_ok, cuda_error = benchmark_throughput_checked("cuda")
         hw["cuda_benchmark_ok"] = cuda_ok
         if cuda_error:
@@ -833,6 +846,7 @@ def run_startup(
             cache_dir=cache_dir,
             debug=debug,
             max_loaded_shards=max_loaded_shards,
+            force_cpu=force_cpu,
         )
         _node_start_time = time.monotonic()
         actual_port = node.start()
@@ -986,6 +1000,7 @@ def run_startup(
             cache_dir=cache_dir,
             debug=debug,
             max_loaded_shards=max_loaded_shards,
+            force_cpu=force_cpu,
         )
         _node_start_time = time.monotonic()
         actual_port = node.start()
@@ -1163,6 +1178,7 @@ def run_startup(
             cache_dir=shard_path,
             debug=debug,
             max_loaded_shards=max_loaded_shards,
+            force_cpu=force_cpu,
         )
         actual_port = node.start()
         total_layers = getattr(getattr(node, "backend", None), "total_layers", None) or assigned_total_layers