[bug]: Runtime error when enable_partial_loading is enabled #8850
Description
Is there an existing issue for this problem?
- I have searched the existing issues
Install method
Docker-Compose
Operating system
Linux
GPU vendor
Nvidia (CUDA)
GPU model
RTX 2060
GPU VRAM
6GB
Version number
6.11.0.post1
Browser
Vivaldi 7.8.3925.56
System Information
{
"version": "6.11.0.post1",
"dependencies": {
"absl-py" : "2.3.1",
"accelerate" : "1.8.1",
"annotated-types" : "0.7.0",
"anyio" : "4.9.0",
"attrs" : "25.3.0",
"bidict" : "0.23.1",
"bitsandbytes" : "0.46.1",
"blake3" : "1.0.5",
"certifi" : "2025.6.15",
"cffi" : "1.17.1",
"charset-normalizer" : "3.4.2",
"click" : "8.2.1",
"coloredlogs" : "15.0.1",
"compel" : "2.1.1",
"contourpy" : "1.3.2",
"CUDA" : "12.8",
"cycler" : "0.12.1",
"Deprecated" : "1.2.18",
"diffusers" : "0.36.0",
"dnspython" : "2.7.0",
"dynamicprompts" : "0.31.0",
"einops" : "0.8.1",
"fastapi" : "0.118.3",
"fastapi-events" : "0.12.2",
"filelock" : "3.18.0",
"flatbuffers" : "25.2.10",
"fonttools" : "4.58.5",
"fsspec" : "2025.5.1",
"gguf" : "0.17.1",
"h11" : "0.16.0",
"hf-xet" : "1.1.5",
"httpcore" : "1.0.9",
"httptools" : "0.6.4",
"httpx" : "0.28.1",
"huggingface-hub" : "0.34.4",
"humanfriendly" : "10.0",
"idna" : "3.10",
"importlib_metadata" : "8.7.0",
"InvokeAI" : "6.11.0.post1",
"jax" : "0.6.2",
"jaxlib" : "0.6.2",
"Jinja2" : "3.1.6",
"kiwisolver" : "1.4.8",
"MarkupSafe" : "3.0.1",
"matplotlib" : "3.10.3",
"mediapipe" : "0.10.14",
"ml_dtypes" : "0.5.1",
"mpmath" : "1.3.0",
"networkx" : "3.5",
"numpy" : "1.26.4",
"nvidia-cublas-cu12" : "12.8.3.14",
"nvidia-cuda-cupti-cu12" : "12.8.57",
"nvidia-cuda-nvrtc-cu12" : "12.8.61",
"nvidia-cuda-runtime-cu12": "12.8.57",
"nvidia-cudnn-cu12" : "9.7.1.26",
"nvidia-cufft-cu12" : "11.3.3.41",
"nvidia-cufile-cu12" : "1.13.0.11",
"nvidia-curand-cu12" : "10.3.9.55",
"nvidia-cusolver-cu12" : "11.7.2.55",
"nvidia-cusparse-cu12" : "12.5.7.53",
"nvidia-cusparselt-cu12" : "0.6.3",
"nvidia-nccl-cu12" : "2.26.2",
"nvidia-nvjitlink-cu12" : "12.8.61",
"nvidia-nvtx-cu12" : "12.8.55",
"onnx" : "1.16.1",
"onnxruntime" : "1.19.2",
"opencv-contrib-python" : "4.11.0.86",
"opt_einsum" : "3.4.0",
"packaging" : "25.0",
"picklescan" : "0.0.26",
"pillow" : "11.3.0",
"prompt_toolkit" : "3.0.51",
"protobuf" : "4.25.8",
"psutil" : "7.0.0",
"pycparser" : "2.22",
"pydantic" : "2.11.7",
"pydantic-settings" : "2.10.1",
"pydantic_core" : "2.33.2",
"pyparsing" : "3.2.3",
"PyPatchMatch" : "1.0.2",
"python-dateutil" : "2.9.0.post0",
"python-dotenv" : "1.1.1",
"python-engineio" : "4.12.2",
"python-multipart" : "0.0.20",
"python-socketio" : "5.13.0",
"PyWavelets" : "1.8.0",
"PyYAML" : "6.0.2",
"regex" : "2024.11.6",
"requests" : "2.32.4",
"safetensors" : "0.5.3",
"scipy" : "1.16.0",
"semver" : "3.0.4",
"sentencepiece" : "0.2.0",
"setuptools" : "80.9.0",
"simple-websocket" : "1.1.0",
"six" : "1.17.0",
"sniffio" : "1.3.1",
"sounddevice" : "0.5.2",
"spandrel" : "0.4.1",
"starlette" : "0.46.2",
"sympy" : "1.14.0",
"tokenizers" : "0.22.0",
"torch" : "2.7.1+cu128",
"torchsde" : "0.2.6",
"torchvision" : "0.22.1+cu128",
"tqdm" : "4.67.1",
"trampoline" : "0.1.2",
"transformers" : "4.56.0",
"triton" : "3.3.1",
"typing-inspection" : "0.4.1",
"typing_extensions" : "4.14.0",
"urllib3" : "2.5.0",
"uvicorn" : "0.35.0",
"uvloop" : "0.21.0",
"watchfiles" : "1.1.0",
"wcwidth" : "0.2.13",
"websockets" : "15.0.1",
"wrapt" : "1.17.2",
"wsproto" : "1.2.0",
"zipp" : "3.23.0"
},
"config": {
"schema_version": "4.0.2",
"legacy_models_yaml_path": null,
"host": "0.0.0.0",
"port": 9090,
"allow_origins": [],
"allow_credentials": true,
"allow_methods": ["*"],
"allow_headers": ["*"],
"ssl_certfile": null,
"ssl_keyfile": null,
"log_tokenization": false,
"patchmatch": true,
"models_dir": "models",
"convert_cache_dir": "models/.convert_cache",
"download_cache_dir": "models/.download_cache",
"legacy_conf_dir": "configs",
"db_dir": "databases",
"outputs_dir": "outputs",
"custom_nodes_dir": "nodes",
"style_presets_dir": "style_presets",
"workflow_thumbnails_dir": "workflow_thumbnails",
"log_handlers": ["console"],
"log_format": "color",
"log_level": "info",
"log_sql": false,
"log_level_network": "warning",
"use_memory_db": false,
"dev_reload": false,
"profile_graphs": false,
"profile_prefix": null,
"profiles_dir": "profiles",
"max_cache_ram_gb": null,
"max_cache_vram_gb": null,
"log_memory_usage": false,
"model_cache_keep_alive_min": 0,
"device_working_mem_gb": 3,
"enable_partial_loading": true,
"keep_ram_copy_of_weights": true,
"ram": null,
"vram": null,
"lazy_offload": true,
"pytorch_cuda_alloc_conf": "backend:cudaMallocAsync",
"device": "auto",
"precision": "auto",
"sequential_guidance": false,
"attention_type": "auto",
"attention_slice_size": "auto",
"force_tiled_decode": false,
"pil_compress_level": 1,
"max_queue_size": 10000,
"clear_queue_on_startup": false,
"allow_nodes": null,
"deny_nodes": null,
"node_cache_size": 512,
"hashing_algorithm": "blake3_single",
"remote_api_tokens": null,
"scan_models_on_startup": false,
"unsafe_disable_picklescan": false,
"allow_unknown_models": true
},
"set_config_fields": [
"host", "legacy_models_yaml_path", "enable_partial_loading", "pytorch_cuda_alloc_conf",
"port"
]
}
What happened
After updating my docker container to the latest Invoke I started getting an error
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
If I set enable_partial_loading: false I no longer get the error but I do run out of memory
What you expected to happen
I expect invoke to run my model and produce an image.
How to reproduce the problem
It does not depend on any certain models usage. But it does require a prompt such as A vivid, surreal digital artwork depicting a fantastical forest . With NO prompt it seems to produce a picture, usually a person.
Additional context
I have been using Invoke for the past year without issue and it had been a few weeks since the last time I updated it.
Discord username
No response