CUDA problem help please

[vikolaz]

it give me this error, I should have install Cuda toolkit already

To create a public link, set share=True in launch().
ERROR: Exception in ASGI application
Traceback (most recent call last):
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\uvicorn\protocols\http\httptools_impl.py", line 411, in run_asgi
result = await app( # type: ignore[func-returns-value]
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\uvicorn\middleware\proxy_headers.py", line 69, in call
return await self.app(scope, receive, send)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\fastapi\applications.py", line 1054, in call
await super().call(scope, receive, send)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette\applications.py", line 123, in call
await self.middleware_stack(scope, receive, send)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette\middleware\errors.py", line 186, in call
raise exc
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette\middleware\errors.py", line 164, in call
await self.app(scope, receive, _send)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\gradio\route_utils.py", line 707, in call
await self.app(scope, receive, send)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette\middleware\exceptions.py", line 65, in call
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette_exception_handler.py", line 64, in wrapped_app
raise exc
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette_exception_handler.py", line 53, in wrapped_app
await app(scope, receive, sender)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette\routing.py", line 756, in call
await self.middleware_stack(scope, receive, send)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette\routing.py", line 776, in app
await route.handle(scope, receive, send)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette\routing.py", line 297, in handle
await self.app(scope, receive, send)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette\routing.py", line 77, in app
await wrap_app_handling_exceptions(app, request)(scope, receive, send)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette_exception_handler.py", line 64, in wrapped_app
raise exc
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette_exception_handler.py", line 53, in wrapped_app
await app(scope, receive, sender)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette\routing.py", line 75, in app
await response(scope, receive, send)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette\responses.py", line 352, in call
await send(
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette_exception_handler.py", line 50, in sender
await send(message)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette_exception_handler.py", line 50, in sender
await send(message)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\starlette\middleware\errors.py", line 161, in _send
await send(message)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\uvicorn\protocols\http\httptools_impl.py", line 549, in send
raise RuntimeError("Response content shorter than Content-Length")
RuntimeError: Response content shorter than Content-Length
Traceback (most recent call last):
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\gradio\queueing.py", line 527, in process_events
response = await route_utils.call_process_api(
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\gradio\route_utils.py", line 270, in call_process_api
output = await app.get_blocks().process_api(
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\gradio\blocks.py", line 1847, in process_api
result = await self.call_function(
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\gradio\blocks.py", line 1433, in call_function
prediction = await anyio.to_thread.run_sync(
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\anyio_backends_asyncio.py", line 2144, in run_sync_in_worker_thread
return await future
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\anyio_backends_asyncio.py", line 851, in run
result = context.run(func, *args)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\gradio\utils.py", line 805, in wrapper
response = f(*args, **kwargs)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main\infer.py", line 58, in infer_image
free_memory = torch.cuda.mem_get_info()[0]
File "D:_A.I._2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\torch\cuda\memory.py", line 661, in mem_get_info
device = torch.cuda.current_device()
File "D:_A.I.2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\torch\cuda_init.py", line 769, in current_device
_lazy_init()
File "D:_A.I.2024\Lip_Wise-main\Lip_Wise-main.lip-wise\lib\site-packages\torch\cuda_init.py", line 289, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

[pawansharmaaaa]

Install the pytorch-gpu module from here https://pytorch.org/get-started/locally/

[vikolaz]

Hi thanks for the response.
Actually I tried several time to install pytorch-gpu module from https://pytorch.org/get-started/locally/
conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia

For sure there something that I'm doing wrong, I'm not so expert. I don't know if I run the torch command int the right place/folder.

If you can further help would super

Thank you!!

[vikolaz]

I've tried do downgrade the Nvidia Toolkit as I had the 12.1

Now I have reinstalled the Toolkit 11.8 version and reinstalled the releted pytorch

That what my system show i have:

**C:>python -c "import torch; print('PyTorch version:', torch.version)"
PyTorch version: 2.3.0+cu118

C:>python -c "import torchvision; print('Torchvision version:', torchvision.version)"
Torchvision version: 0.18.0+cu118

C:>nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on Wed_Sep_21_10:41:10_Pacific_Daylight_Time_2022
Cuda compilation tools, release 11.8, V11.8.89
Build cuda_11.8.r11.8/compiler.31833905_0**

[pawansharmaaaa]

Hello, I don't think that this is a problem with your cuda toolkit, it is an issue with pytorch installation. Did you run setup script?

[vikolaz]

Yes i did, also tried to delete the folder and start a fresh setup

[pawansharmaaaa]

Do one thing, activate the environment and install pytorch-gpu with pip

[vikolaz]

Yesss that solved the issue!!

Thank you very much