Found no NVIDIA driver on your system

[Micahel-Kochetov]

I have RX7900XTX no Nvidia, here is my COMMANDLINE_ARGS

set COMMANDLINE_ARGS= --skip-torch-cuda-test --opt-split-attention-invokeai --no-half-vae --no-half --disable-gpu-warning

Python 3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)] Version: f2.0.1v1.10.1-1.10.1 Commit hash: a923f7bcc4a376c78c8b5fd8d563a87ddbacfc43 Launching Web UI with arguments: --skip-torch-cuda-test --opt-split-attention-invokeai --no-half-vae --no-half --disable-gpu-warning Traceback (most recent call last): File "E:\WebUI forge\stable-diffusion-webui-amdgpu-forge\launch.py", line 54, in main() File "E:\WebUI forge\stable-diffusion-webui-amdgpu-forge\launch.py", line 50, in main start() File "E:\WebUI forge\stable-diffusion-webui-amdgpu-forge\modules\launch_utils.py", line 682, in start import webui File "E:\WebUI forge\stable-diffusion-webui-amdgpu-forge\webui.py", line 21, in initialize_forge() File "E:\WebUI forge\stable-diffusion-webui-amdgpu-forge\modules_forge\initialization.py", line 58, in initialize_forge from backend import memory_management File "E:\WebUI forge\stable-diffusion-webui-amdgpu-forge\backend\memory_management.py", line 133, in total_vram = get_total_memory(get_torch_device()) / (1024 * 1024) File "E:\WebUI forge\stable-diffusion-webui-amdgpu-forge\backend\memory_management.py", line 100, in get_torch_device return torch.device(torch.cuda.current_device()) File "E:\WebUI forge\stable-diffusion-webui-amdgpu-forge\venv\lib\site-packages\torch\cuda_init_.py", line 778, in current_device lazy_init() File "E:\WebUI forge\stable-diffusion-webui-amdgpu-forge\venv\lib\site-packages\torch\cuda_init.py", line 293, in _lazy_init torch._C._cuda_init() RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx Press any key to continue . . .

[lshqqytiger]

1. Remove --skip-torch-cuda-test. It is like, "I want to use CPU."
2. Instead, add --use-zluda.
3. Remove --no-half and --no-half-vae. They are needed if you are using one of too old cards to run fp16 operations in hardware level. However, you are on RX 7900 XTX, which is one of the really decent cards. They will make your generation at least 2x slower.
4. Remove --opt-split-attention-invokeai. Forge will choose the optimal one for you.
5. Remove venv folder and launch webui.

[esanscoopsers]

I had this same issue using ./webui.sh --use-zluda i am on archlinux with a 6700XT

[lshqqytiger]

Please use native ROCm on Linux.