[bug]: After installing, any generation close the Invoke giving an error...

[telles0808]

Is there an existing issue for this problem?

• I have searched the existing issues

Install method

Invoke's Launcher

Operating system

Windows

GPU vendor

Nvidia (CUDA)

GPU model

GTX 1060 Max-Q

GPU VRAM

6GB

Version number

lastest v1.7.1

Browser

edge

System Information

Started Invoke process with PID 28000
[2025-09-10 11:38:19,917]::[InvokeAI]::INFO --> Using torch device: NVIDIA GeForce GTX 1060 with Max-Q D
esign
[2025-09-10 11:38:21,004]::[InvokeAI]::INFO --> cuDNN version: 90701
[2025-09-10 11:38:23,652]::[InvokeAI]::INFO --> Patchmatch initialized
[2025-09-10 11:38:25,001]::[InvokeAI]::INFO --> InvokeAI version 6.6.0
[2025-09-10 11:38:25,002]::[InvokeAI]::INFO --> Root directory = C:\InvokeAI
[2025-09-10 11:38:25,006]::[InvokeAI]::INFO --> Initializing database at C:\InvokeAI\databases\invokeai.
db
[2025-09-10 11:38:26,247]::[ModelManagerService]::INFO --> [MODEL CACHE] Calculated model RAM cache size
: 4096.00 MB. Heuristics applied: [1, 2, 3].
[2025-09-10 11:38:26,426]::[InvokeAI]::INFO --> Invoke running on http://127.0.0.1:9090 (Press CTRL+C to
quit)
[2025-09-10 11:38:47,970]::[InvokeAI]::INFO --> Executing queue item 6, session 9113aa97-9fbf-4adf-8919-
c6852d6ae786
[2025-09-10 11:38:50,459]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model 'a80985c8-7e1a-4ce
7-b398-229e757a0c93:text_encoder_2' (T5EncoderModel) onto cuda device in 1.78s. Total model size: 4922.1
4MB, VRAM: 1104.00MB (22.4%)
You set add_prefix_space. The tokenizer needs to be converted from the slow tokenizers
[2025-09-10 11:38:50,767]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model 'a80985c8-7e1a-4ce
7-b398-229e757a0c93:tokenizer_2' (T5TokenizerFast) onto cuda device in 0.00s. Total model size: 0.03MB,
VRAM: 0.00MB (0.0%)
C:\InvokeAI.venv\Lib\site-packages\bitsandbytes\autograd_functions.py:186: UserWarning: MatMul8bitLt:
inputs will be cast from torch.bfloat16 to float16 during quantization
warnings.warn(f"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization")
Error named symbol not found at line 448 in file D:\a\bitsandbytes\bitsandbytes\csrc\ops.cu
Invoke process exited with code 1

What happened

after installing Flux Kotext the following error happen...

What you expected to happen

generate the image..

How to reproduce the problem

No response

Additional context

No response

Discord username

No response