Distributed setup now defaults to panicking when out of memory now, to facilitate graceful recovery

comfy/cli_args.py

@@ -194,7 +194,7 @@ def _create_parser() -> EnhancedConfigArgParser:
         '--panic-when',
         action='append',
         help="""
-        List of fully qualified exception class names to panic (os.exit(1)) when a workflow raises it.
+        List of fully qualified exception class names to panic (sys.exit(1)) when a workflow raises it.
         Example: --panic-when=torch.cuda.OutOfMemoryError. Can be specified multiple times or as a 
         comma-separated list.""",
         type=str,

comfy/cli_args_types.py

@@ -122,7 +122,7 @@ class Configuration(dict):
         anthropic_api_key (str): Configures the Anthropic API key for its nodes related to Claude functionality. Visit https://console.anthropic.com/settings/keys to create this key.
         user_directory (Optional[str]): Set the ComfyUI user directory with an absolute path.
         log_stdout (bool): Send normal process output to stdout instead of stderr (default)
-        panic_when (list[str]): List of fully qualified exception class names to panic (os.exit(1)) when a workflow raises it.
+        panic_when (list[str]): List of fully qualified exception class names to panic (sys.exit(1)) when a workflow raises it.
     """
 
     def __init__(self, **kwargs):

docker-compose.yml

@@ -16,6 +16,8 @@ services:
               capabilities: [ gpu ]
     environment:
       - COMFYUI_DISTRIBUTED_QUEUE_CONNECTION_URI=amqp://guest:guest@rabbitmq:5672
+      - COMFYUI_EXECUTOR_FACTORY=ProcessPoolExecutor
+      - COMFYUI_PANIC_WHEN=torch.cuda.OutOfMemoryError
       - COMFYUI_LOGGING_LEVEL=ERROR
     command:
       - comfyui-worker