Skip to content

Dynamic_vram: Remove Aimdo exemption for empty_cache (fixes VRAM leak) #12260

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
comfyanonymous merged 1 commit into from
Feb 4, 2026
Merged

Dynamic_vram: Remove Aimdo exemption for empty_cache (fixes VRAM leak) #12260

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 3 additions & 5 deletions comfy/model_management.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1724,11 +1724,9 @@ def soft_empty_cache(force=False):
elif is_mlu():
torch.mlu.empty_cache()
elif torch.cuda.is_available():
if comfy.memory_management.aimdo_allocator is None:
#Pytorch 2.7 and earlier crashes if you try and empty_cache when mempools exist
torch.cuda.synchronize()
torch.cuda.empty_cache()
torch.cuda.ipc_collect()
torch.cuda.synchronize()
torch.cuda.empty_cache()
torch.cuda.ipc_collect()

def unload_all_models():
free_memory(1e30, get_torch_device())
Expand Down
7 changes: 5 additions & 2 deletions main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,7 +192,10 @@ def execute_script(script_path):
import comfy_aimdo.torch

if enables_dynamic_vram():
if comfy_aimdo.control.init_device(comfy.model_management.get_torch_device().index):
if comfy.model_management.torch_version_numeric < (2, 8):
logging.warning("Unsupported Pytorch detected. DynamicVRAM support requires Pytorch version 2.8 or later. Falling back to legacy ModelPatcher. VRAM estimates may be unreliable especially on Windows")
comfy.memory_management.aimdo_allocator = None
elif comfy_aimdo.control.init_device(comfy.model_management.get_torch_device().index):
if args.verbose == 'DEBUG':
comfy_aimdo.control.set_log_debug()
elif args.verbose == 'CRITICAL':
Expand All @@ -208,7 +211,7 @@ def execute_script(script_path):
comfy.memory_management.aimdo_allocator = comfy_aimdo.torch.get_torch_allocator()
logging.info("DynamicVRAM support detected and enabled")
else:
logging.info("No working comfy-aimdo install detected. DynamicVRAM support disabled. Falling back to legacy ModelPatcher. VRAM estimates may be unreliable especially on Windows")
logging.warning("No working comfy-aimdo install detected. DynamicVRAM support disabled. Falling back to legacy ModelPatcher. VRAM estimates may be unreliable especially on Windows")
comfy.memory_management.aimdo_allocator = None


Expand Down