Cant Launch with my M40 24Gbs GPU

[zarigata]

Is there an existing issue for this?

• I have searched the existing issues and checked the recent builds/commits

What happened?

ive installed cuda and drivers for the GPU but it deploys with an error

LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
loading stable diffusion model: RuntimeError
Traceback (most recent call last):
  File "C:\Users\AI\Desktop\stable-diffusion-webui-1.2.1\modules\sd_models.py", line 419, in get_sd_model
    load_model()
  File "C:\Users\AI\Desktop\stable-diffusion-webui-1.2.1\modules\sd_models.py", line 481, in load_model
    load_model_weights(sd_model, checkpoint_info, state_dict, timer)
  File "C:\Users\AI\Desktop\stable-diffusion-webui-1.2.1\modules\sd_models.py", line 335, in load_model_weights
    model.logvar = model.logvar.to(devices.device)  # fix for training
RuntimeError: CUDA error: CUDA-capable device(s) is/are busy or unavailable
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

Steps to reproduce the problem

1. Reinstalled all the files
2. open the webui.bat
3. wait for some time
4. Error apeared

What should have happened?

run in normal mode

Commit where the problem happens

commit 89f9faa

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

--listen

List of extensions

No

Console logs

LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
loading stable diffusion model: RuntimeError
Traceback (most recent call last):
  File "C:\Users\AI\Desktop\stable-diffusion-webui-1.2.1\modules\sd_models.py", line 419, in get_sd_model
    load_model()
  File "C:\Users\AI\Desktop\stable-diffusion-webui-1.2.1\modules\sd_models.py", line 481, in load_model
    load_model_weights(sd_model, checkpoint_info, state_dict, timer)
  File "C:\Users\AI\Desktop\stable-diffusion-webui-1.2.1\modules\sd_models.py", line 335, in load_model_weights
    model.logvar = model.logvar.to(devices.device)  # fix for training
RuntimeError: CUDA error: CUDA-capable device(s) is/are busy or unavailable
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

### Additional information

Using on Windows 10 pro 
Intel i7
32gbs DDR4
M40 GPU 24 Gbs

[zarigata]

Fixed the traceback but still has the problem of main.py

Traceback (most recent call last):
  File "C:\Users\AI\Desktop\FEVER\webui\launch.py", line 325, in <module>
    start()
  File "C:\Users\AI\Desktop\FEVER\webui\launch.py", line 320, in start
    webui.webui()
  File "C:\Users\AI\Desktop\FEVER\webui\webui.py", line 224, in webui
    app.add_middleware(GZipMiddleware, minimum_size=1000)
  File "C:\Users\AI\Desktop\FEVER\system\python\lib\site-packages\starlette\applications.py", line 139, in add_middleware
    raise RuntimeError("Cannot add middleware after an application has started")
RuntimeError: Cannot add middleware after an application has started

[chrme]

#7759

[zarigata]

FIXED!!!! Thank You @chrme

[gpl666]

Fixed the traceback but still has the problem of main.py

Traceback (most recent call last):
  File "C:\Users\AI\Desktop\FEVER\webui\launch.py", line 325, in <module>
    start()
  File "C:\Users\AI\Desktop\FEVER\webui\launch.py", line 320, in start
    webui.webui()
  File "C:\Users\AI\Desktop\FEVER\webui\webui.py", line 224, in webui
    app.add_middleware(GZipMiddleware, minimum_size=1000)
  File "C:\Users\AI\Desktop\FEVER\system\python\lib\site-packages\starlette\applications.py", line 139, in add_middleware
    raise RuntimeError("Cannot add middleware after an application has started")
RuntimeError: Cannot add middleware after an application has started

How did you manage to fix the traceback?

[zarigata]

Fixed the traceback but still has the problem of main.py

Traceback (most recent call last):
  File "C:\Users\AI\Desktop\FEVER\webui\launch.py", line 325, in <module>
    start()
  File "C:\Users\AI\Desktop\FEVER\webui\launch.py", line 320, in start
    webui.webui()
  File "C:\Users\AI\Desktop\FEVER\webui\webui.py", line 224, in webui
    app.add_middleware(GZipMiddleware, minimum_size=1000)
  File "C:\Users\AI\Desktop\FEVER\system\python\lib\site-packages\starlette\applications.py", line 139, in add_middleware
    raise RuntimeError("Cannot add middleware after an application has started")
RuntimeError: Cannot add middleware after an application has started

How did you manage to fix the traceback?

If i can remember ive reinstalled cuda and nvidia drivers as well as directx 11.... dont remember what exactly was