Broken on Metal: why is ooba attempting to import llama_cpp_cuda ?

[cm8t]

Describe the bug

Exception: Cannot import 'llama_cpp_cuda' because 'llama_cpp' is already imported. See issue #1575 in llama-cpp-python. Please restart the server before attempting to use a different version of llama-cpp-python.

Is there an existing issue for this?

• I have searched the existing issues

Reproduction

fresh install, start server, attempt to load model

Screenshot

No response

Logs

start_macos.sh
15:32:05-639275 INFO     Starting Text generation web UI                        

Running on local URL:  http://127.0.0.1:7860

15:32:14-027478 INFO     Loading "Codestral-22B-v0.1-Q5_K_M.gguf"               
15:32:14-057944 INFO     llama.cpp weights detected:                            
                         "models/Codestral-22B-v0.1-Q5_K_M.gguf"                
15:32:14-086935 ERROR    Failed to load the model.                              
Traceback (most recent call last):
  File "/Users/CM/Downloads/text-generation-webui-main-2/modules/ui_model_menu.py", line 246, in load_model_wrapper
    shared.model, shared.tokenizer = load_model(selected_model, loader)
                                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/CM/Downloads/text-generation-webui-main-2/modules/models.py", line 94, in load_model
    output = load_func_map[loader](model_name)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/CM/Downloads/text-generation-webui-main-2/modules/models.py", line 275, in llamacpp_loader
    model, tokenizer = LlamaCppModel.from_pretrained(model_file)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/CM/Downloads/text-generation-webui-main-2/modules/llamacpp_model.py", line 39, in from_pretrained
    LlamaCache = llama_cpp_lib().LlamaCache
                 ^^^^^^^^^^^^^^^
  File "/Users/CM/Downloads/text-generation-webui-main-2/modules/llama_cpp_python_hijack.py", line 38, in llama_cpp_lib
    raise Exception(f"Cannot import 'llama_cpp_cuda' because '{imported_module}' is already imported. See issue #1575 in llama-cpp-python. Please restart the server before attempting to use a different version of llama-cpp-python.")
Exception: Cannot import 'llama_cpp_cuda' because 'llama_cpp' is already imported. See issue #1575 in llama-cpp-python. Please restart the server before attempting to use a different version of llama-cpp-python.

System Info

M1 Max 32GB  Sonoma 14.6

[OceanSurfer]

abetlen/llama-cpp-python#1575