Issue
When you run the program and come back after a few hours to run the program you get a Runtime error. This error occurs when the program tries to load the embedding model onto the GPU.
Error Message
RuntimeError: CUDA error: CUDA-capable device(s) is/are busy or unavailable
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
Temporary Fix
Restart your computer to clear the GPU's memory and allow the embedding model to load properly. I have done some investigating in nvidia-smi and it seems nothing is loaded into the GPU so I'm not sure what is causing the error.
Issue
When you run the program and come back after a few hours to run the program you get a Runtime error. This error occurs when the program tries to load the embedding model onto the GPU.
Error Message
Temporary Fix
Restart your computer to clear the GPU's memory and allow the embedding model to load properly. I have done some investigating in nvidia-smi and it seems nothing is loaded into the GPU so I'm not sure what is causing the error.