check port availability only in main launcher for deepspeed/torchrun

huggingface · Oct 25, 2023 · 498e756 · 498e756
1 parent 9cd5f8c
commit 498e756
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/src/accelerate/utils/launch.py b/src/accelerate/utils/launch.py
@@ -128,7 +128,8 @@ def prepare_multi_gpu_env(args: argparse.Namespace) -> Dict[str, str]:
     if main_process_port is None:
         main_process_port = 29500
 
-    if is_port_in_use(main_process_port):
+    need_port_check = num_machines <= 1 or int(args.machine_rank) == 0
+    if need_port_check and is_port_in_use(main_process_port):
         raise ConnectionError(
             f"Tried to launch distributed communication on port `{main_process_port}`, but another process is utilizing it. "
             "Please specify a different port (such as using the `----main_process_port` flag or specifying a different `main_process_port` in your config file)"