This allows elevenlabs Clients to work automatically with LocalAI by supporting the elevenlabs API. The elevenlabs server endpoint is implemented such as it is wired to the TTS endpoints. Fixes: https://github.com/mudler/LocalAI/issues/1809
* Bump vLLM version to 0.3.2 * Add vLLM model loading options * Remove transformers-exllama * Fix install exllama
* backends(transformers): use AutoModel with LLM types * examples: animagine-xl * Add codellama examples
* feat: add coqui * docs: update news