What happened?
Invoke.AI launch fails after last update - see error messages below
Exception Details
[2025-05-29 18:11:31,137]::[InvokeAI]::INFO --> Using torch device: CPU
The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
PyTorch 2.7.0+cu126 with CUDA 1206 (you have 2.7.0+cpu)
Python 3.10.11 (you have 3.10.11)
Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
Memory-efficient attention, SwiGLU, sparse and more won't be available.
Set XFORMERS_MORE_DETAILS=1 for more details
Traceback (most recent call last):
File "", line 3, in
File "C:\Apps\StabilityMatrix\Data\Packages\InvokeAI\invokeai\app\run_app.py", line 57, in run_app
apply_monkeypatches()
File "C:\Apps\StabilityMatrix\Data\Packages\InvokeAI\invokeai\app\util\startup_utils.py", line 66, in apply_monkeypatches
import invokeai.backend.util.hotfixes # noqa: F401 (monkeypatching on import)
File "C:\Apps\StabilityMatrix\Data\Packages\InvokeAI\invokeai\backend\util\hotfixes.py", line 7, in
from diffusers.models.attention_processor import AttentionProcessor, AttnProcessor
File "C:\Apps\StabilityMatrix\Data\Packages\InvokeAI\venv\lib\site-packages\diffusers\models\attention_processor.py", line 35, in
import xformers.ops
File "C:\Apps\StabilityMatrix\Data\Packages\InvokeAI\venv\lib\site-packages\xformers\ops_init_.py", line 9, in
from .fmha import (
File "C:\Apps\StabilityMatrix\Data\Packages\InvokeAI\venv\lib\site-packages\xformers\ops\fmha_init_.py", line 10, in
from . import (
File "C:\Apps\StabilityMatrix\Data\Packages\InvokeAI\venv\lib\site-packages\xformers\ops\fmha\flash.py", line 55, in
from ... import _C_flashattention # type: ignore[attr-defined]
ImportError: DLL load failed while importing _C_flashattention: The specified module could not be found.
Version
v2.14.2
What Operating System are you using?
Windows
LykosAI
