{"library":"comfy-aimdo","type":"library","category":null,"description":"Comfy AIMDO (AI Model Dynamic Offloader) is a core utility for ComfyUI, acting as a PyTorch VRAM allocator. It implements on-demand offloading of model weights when the primary PyTorch VRAM allocator comes under pressure, aiming to prevent out-of-memory errors and optimize GPU memory usage for AI models. It is currently at version 0.2.12 and is actively maintained as an integral part of the ComfyUI ecosystem.","language":"python","status":"active","version":"0.2.12","tags":["ComfyUI","VRAM","memory management","PyTorch","AI models","GPU"],"last_verified":"Thu May 21","install":[{"cmd":"pip install comfy-aimdo","imports":["import comfy_aimdo.control"]},{"cmd":"cd ComfyUI_DIRECTORY\nvirtual_env_path\\python.exe -m pip install comfy-aimdo","imports":[]}],"homepage":null,"github":"https://github.com/Comfy-Org/comfy-aimdo","docs":null,"changelog":null,"pypi":"https://pypi.org/project/comfy-aimdo/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":100,"avg_install_s":1.6,"avg_import_s":0.06,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/comfy-aimdo/compatibility"}}