[08/06/25 22:46:54] INFO     Starting gunicorn 23.0.0                           
[08/06/25 22:46:54] INFO     Listening at: http://[::]:3003 (8)                 
[08/06/25 22:46:54] INFO     Using worker: immich_ml.config.CustomUvicornWorker 
[08/06/25 22:46:54] INFO     Booting worker with pid: 9                         
[08/06/25 22:46:56] INFO     Started server process [9]                         
[08/06/25 22:46:56] INFO     Waiting for application startup.                   
[08/06/25 22:46:56] INFO     Created in-memory cache with unloading after 300s  
                             of inactivity.                                     
[08/06/25 22:46:56] INFO     Initialized request thread pool with 4 threads.    
[08/06/25 22:46:56] INFO     Application startup complete.                      
[08/06/25 22:47:24] INFO     Loading detection model 'buffalo_l' to memory      
[08/06/25 22:47:24] INFO     Setting execution providers to                     
                             ['CUDAExecutionProvider', 'CPUExecutionProvider'], 
                             in descending order of preference                  
*************** EP Error ***************
EP Error /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_execution_provider_info.cc:59 static onnxruntime::CUDAExecutionProviderInfo onnxruntime::CUDAExecutionProviderInfo::FromProviderOptions(const onnxruntime::ProviderOptions&) [ONNXRuntimeError] : 1 : FAIL : provider_options_utils.h:151 Parse Failed to parse provider option "device_id": CUDA failure 999: unknown error ; GPU=-1 ; hostname=06ced1f5edef ; file=/onnxruntime_src/onnxruntime/core/providers/cuda/cuda_execution_provider_info.cc ; line=66 ; expr=cudaGetDeviceCount(&num_devices); 
 when using ['CUDAExecutionProvider', 'CPUExecutionProvider']
Falling back to ['CPUExecutionProvider'] and retrying.
****************************************
[08/06/25 22:47:24] INFO     Loading recognition model 'buffalo_l' to memory    
[08/06/25 22:47:24] INFO     Setting execution providers to                     
                             ['CUDAExecutionProvider', 'CPUExecutionProvider'], 
                             in descending order of preference                  
*************** EP Error ***************
EP Error /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_execution_provider_info.cc:59 static onnxruntime::CUDAExecutionProviderInfo onnxruntime::CUDAExecutionProviderInfo::FromProviderOptions(const onnxruntime::ProviderOptions&) [ONNXRuntimeError] : 1 : FAIL : provider_options_utils.h:151 Parse Failed to parse provider option "device_id": CUDA failure 999: unknown error ; GPU=-1 ; hostname=06ced1f5edef ; file=/onnxruntime_src/onnxruntime/core/providers/cuda/cuda_execution_provider_info.cc ; line=66 ; expr=cudaGetDeviceCount(&num_devices); 
 when using ['CUDAExecutionProvider', 'CPUExecutionProvider']
Falling back to ['CPUExecutionProvider'] and retrying.
****************************************
[08/06/25 22:52:46] INFO     Shutting down due to inactivity.                   
[08/06/25 22:52:46] INFO     Shutting down                                      
[08/06/25 22:52:46] INFO     Waiting for application shutdown.                  
[08/06/25 22:52:46] INFO     Application shutdown complete.                     
[08/06/25 22:52:46] INFO     Finished server process [9]                        
[08/06/25 22:52:46] ERROR    Worker (pid:9) was sent SIGINT!                    
[08/06/25 22:52:46] INFO     Booting worker with pid: 116                       
[08/06/25 22:52:47] INFO     Started server process [116]                       
[08/06/25 22:52:47] INFO     Waiting for application startup.                   
[08/06/25 22:52:47] INFO     Created in-memory cache with unloading after 300s  
                             of inactivity.                                     
[08/06/25 22:52:47] INFO     Initialized request thread pool with 4 threads.    
[08/06/25 22:52:47] INFO     Application startup complete.