Merge pull request #94 from apoorvkh/default-agent-timeout

Decreased default agent timeout to 60s

Author: apoorvkh

src/torchrunx/integrations/cli.py

@@ -55,8 +55,8 @@ def add_torchrunx_argument_group(parser: ArgumentParser) -> None:
     group.add_argument(
         "--agent-timeout",
         type=int,
-        default=180,
-        help="Agent communication timeout in seconds. Default: 180.",
+        default=60,
+        help="Agent communication timeout in seconds. Default: 60.",
     )
 
     group.add_argument(

src/torchrunx/launcher.py

@@ -63,7 +63,7 @@ class Launcher:
         Use GLOO for CPU backend. ``None`` for no process group."""
     worker_timeout: int = 600
     """Worker process group timeout (seconds)."""
-    agent_timeout: int = 180
+    agent_timeout: int = 60
     """Agent communication timeout (seconds)."""
     copy_env_vars: tuple[str, ...] = DEFAULT_ENV_VARS_FOR_COPY
     """Environment variables to copy from the launcher process to workers.