Skip to content

Embedding Model Runtime Error #6

Description

@JakeFurtaw

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.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions