Print memory summary on OOM to help with debugging.

comfy/model_management.py

@@ -1542,6 +1542,10 @@ def soft_empty_cache(force=False):
 def unload_all_models():
     free_memory(1e30, get_torch_device())
 
+def debug_memory_summary():
+    if is_amd() or is_nvidia():
+        return torch.cuda.memory.memory_summary()
+    return ""
 
 #TODO: might be cleaner to put this somewhere else
 import threading

execution.py

@@ -601,6 +601,7 @@ async def execute(server, dynprompt, caches, current_item, extra_data, executed,
 
         if isinstance(ex, comfy.model_management.OOM_EXCEPTION):
             tips = "This error means you ran out of memory on your GPU.\n\nTIPS: If the workflow worked before you might have accidentally set the batch_size to a large number."
+            logging.info("Memory summary: {}".format(comfy.model_management.debug_memory_summary()))
             logging.error("Got an OOM, unloading all loaded models.")
             comfy.model_management.unload_all_models()