runtime error

Exit code: 1. Reason: /home/user/.local/lib/python3.10/site-packages/bitsandbytes/cextension.py:34: UserWarning: The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable. warn("The installed version of bitsandbytes was compiled without GPU support. " /home/user/.local/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cpu.so: undefined symbol: cadam32bit_grad_fp32 [2026-04-16 02:06:07,774] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) 2026-04-16 02:06:15 | INFO | gradio_web_server | args: Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:10000', concurrency_count=8, model_list_mode='reload', share=False, moderate=False, embed=False) 2026-04-16 02:06:15 | INFO | gradio_web_server | Starting the controller 2026-04-16 02:06:15 | INFO | gradio_web_server | Starting the model worker for the model liuhaotian/llava-v1.5-13b 2026-04-16 02:06:25 | INFO | stdout | HTTPConnectionPool(host='localhost', port=10000): Max retries exceeded with url: /refresh_all_workers (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f45fa28e020>: Failed to establish a new connection: [Errno 111] Connection refused'))

Container logs: