CUDA_HOME variable not set

[EidosL]

The error says I did not have raise OSError('CUDA_HOME environment variable is not set. '

but when I check
E:\exui>nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Wed_Nov_22_10:30:42_Pacific_Standard_Time_2023
Cuda compilation tools, release 12.3, V12.3.107
Build cuda_12.3.r12.3/compiler.33567101_0

here is the complete log

Traceback (most recent call last):
File "E:\exui\server.py", line 11, in
from backend.models import update_model, load_models, get_model_info, list_models, remove_model, load_model, unload_model, get_loaded_model
File "E:\exui\backend\models.py", line 5, in
from exllamav2 import(
File "C:\Users\LEE.pyenv\pyenv-win\versions\3.11.0\Lib\site-packages\exllamav2_init_.py", line 3, in
from exllamav2.model import ExLlamaV2
File "C:\Users\LEE.pyenv\pyenv-win\versions\3.11.0\Lib\site-packages\exllamav2\model.py", line 23, in
from exllamav2.config import ExLlamaV2Config
File "C:\Users\LEE.pyenv\pyenv-win\versions\3.11.0\Lib\site-packages\exllamav2\config.py", line 2, in
from exllamav2.fasttensors import STFile
File "C:\Users\LEE.pyenv\pyenv-win\versions\3.11.0\Lib\site-packages\exllamav2\fasttensors.py", line 5, in
from exllamav2.ext import exllamav2_ext as ext_c
File "C:\Users\LEE.pyenv\pyenv-win\versions\3.11.0\Lib\site-packages\exllamav2\ext.py", line 153, in
exllamav2_ext = load
^^^^^^
File "C:\Users\LEE.pyenv\pyenv-win\versions\3.11.0\Lib\site-packages\torch\utils\cpp_extension.py", line 1306, in load
return _jit_compile(
^^^^^^^^^^^^^
File "C:\Users\LEE.pyenv\pyenv-win\versions\3.11.0\Lib\site-packages\torch\utils\cpp_extension.py", line 1710, in _jit_compile
_write_ninja_file_and_build_library(
File "C:\Users\LEE.pyenv\pyenv-win\versions\3.11.0\Lib\site-packages\torch\utils\cpp_extension.py", line 1800, in _write_ninja_file_and_build_library
extra_ldflags = _prepare_ldflags(
^^^^^^^^^^^^^^^^^
File "C:\Users\LEE.pyenv\pyenv-win\versions\3.11.0\Lib\site-packages\torch\utils\cpp_extension.py", line 1887, in _prepare_ldflags
extra_ldflags.append(f'/LIBPATH:{_join_cuda_home("lib", "x64")}')
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\LEE.pyenv\pyenv-win\versions\3.11.0\Lib\site-packages\torch\utils\cpp_extension.py", line 2407, in _join_cuda_home
raise OSError('CUDA_HOME environment variable is not set. '
OSError: CUDA_HOME environment variable is not set. Please set it to your CUDA install root.

E:\exui>nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Wed_Nov_22_10:30:42_Pacific_Standard_Time_2023
Cuda compilation tools, release 12.3, V12.3.107
Build cuda_12.3.r12.3/compiler.33567101_0

[ElfrinoGem]

I'm getting the same error.

[dsent]

I get the same error, despite having installed precompiled versions of torch and exllamav2, as per the instruction.

[zero-stroke]

I was able to fix this with this in an admin cmd:
setx CONDA_HOME "C:\ProgramData\anaconda3"
Then closing all cmd windows and reopening and trying again.

[dancost]

I was able to fix this with this in an admin cmd: setx CONDA_HOME "C:\ProgramData\anaconda3" Then closing all cmd windows and reopening and trying again.

I think you are confusing CONDA_HOME with CUDA_HOME. The issue here, as stated in the error, is that CUDA_HOME is not set.