Face Detection Error (CUDA runtime version)
I'm getting the following error when I try and run face detection in Immich.
I'm running this through docker on Unraid. I've tried setting
*************** EP Error ***************
EP Error /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:121 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, ERRTYPE, const char*, const char*, int) [with ERRTYPE = cudaError; bool THRW = true; std::conditional_t<THRW, void, onnxruntime::common::Status> = void] /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:114 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, ERRTYPE, const char*, const char*, int) [with ERRTYPE = cudaError; bool THRW = true; std::conditional_t<THRW, void, onnxruntime::common::Status> = void] CUDA failure 35: CUDA driver version is insufficient for CUDA runtime version ; GPU=0 ; hostname=310fec5ac57b ; file=/onnxruntime_src/onnxruntime/core/providers/cuda/cuda_execution_provider.cc ; line=245 ; expr=cudaSetDevice(info_.device_id);I'm running this through docker on Unraid. I've tried setting
NVIDIA_VISIBLE_DEVICES to my gpuid and NVIDIA_DRIVER_CAPABILITIES to all (although I'm not sure this is necessary because from what I've seen it looks like dockerfile just sets these to all. I've also set MACHINE_LEARNING_GPU_ACCELERATION to cuda. I only have a 1050ti (maybe this card is too old?) but it's running the latest drivers available in the unraid nvidia plugin (this was after upgrading from 545.[something]). Attached is my nvidia-smi output (I don't have the output from prior to the driver upgrade).
