Issue: Local LLM Integration Not Available as a Conversation Agent

[haltdurchdigger]

Description:
I’ve installed the Local LLM integration from HACS. When adding the integration, I selected Llama.cpp (HuggingFace). The model I chose is acon96/Home-3B-GGUF, and the model files were successfully downloaded to /media/models.

However, when I try to configure the voice assistant, the Local LLM option does not appear as an available conversation agent. According to the logs, it seems that the conversation platform is not launching.

Steps to Reproduce:
1. Install the Local LLM integration via HACS.
2. Add the integration and select Llama.cpp (HuggingFace).
3. Choose the model acon96/Home-3B-GGUF.
4. Verify that the model files are downloaded to /media/models.
5. Attempt to configure the voice assistant and look for Local LLM as a conversation agent.

Expected Behavior:
The Local LLM option should appear as a selectable conversation agent.

Logs:

Logger: homeassistant.components.conversation
Quelle: helpers/entity_platform.py:366
Integration: Konversation (Dokumentation, Probleme)
Erstmals aufgetreten: 00:51:33 (4 Vorkommnisse)
Zuletzt protokolliert: 03:22:02

Error while setting up llama_conversation platform for conversation
Traceback (most recent call last):
  File "/usr/src/homeassistant/homeassistant/helpers/entity_platform.py", line 366, in _async_setup_platform
    await asyncio.shield(awaitable)
  File "/config/custom_components/llama_conversation/conversation.py", line 179, in async_setup_entry
    await agent._async_load_model(entry)
  File "/config/custom_components/llama_conversation/conversation.py", line 282, in _async_load_model
    return await self.hass.async_add_executor_job(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
        self._load_model, entry
        ^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/usr/local/lib/python3.13/concurrent/futures/thread.py", line 59, in run
    result = self.fn(*self.args, **self.kwargs)
  File "/config/custom_components/llama_conversation/conversation.py", line 895, in _load_model
    validate_llama_cpp_python_installation()
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^
  File "/config/custom_components/llama_conversation/utils.py", line 151, in validate_llama_cpp_python_installation
    raise Exception(f"Failed to properly initialize llama-cpp-python. (Exit code {process.exitcode}.)")
Exception: Failed to properly initialize llama-cpp-python. (Exit code -4.)

Environment:
• Home Assistant Version: 2025.1.4 x86
• Local LLM Integration Version: 0.3.7
• HACS Version: 2.0.3
• Hardware: Dell Wyse 5070, Intel Celeron J4105 | 32GB DDR4

Any suggestions on troubleshooting steps or possible misconfigurations would be appreciated.

[acon96]

Please follow the workaround listed here: https://github.com/acon96/home-llm/blob/develop/docs/Backend%20Configuration.md#wheels

I recently got a Celeron Mini PC in to try to start adding builds for those processors.