How can I run this docker on a non-CUDA Intel Iris Xe GPU?

[Ease78]

This is the error that I am getting right now:

Error invoking remote method 'docker-start-container': Error: (HTTP code 500) server error - failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error running hook #0: error running hook: exit status 1, stdout: , stderr:

Auto-detected mode as 'legacy' nvidia-container-cli: initialization error: WSL environment detected but no adapters were found: unknown

[lazarst96]

Hi,

You can't run this environment on your GPU, but you can run it on the CPU. Please note - That can cause losing some performance.

You can try with the following changes:

1. Change the following code snippet from docker-compose

tf-serving:
  image: tensorflow/serving:latest-gpu

to:

tf-serving:
  image: tensorflow/serving:latest

2. Remove the following part of docker-compose:

deploy:
    resources:
      reservations:
        devices:
          - driver: "nvidia"
            capabilities: [ gpu ]

[Ease78]

"Failed to start server. Error: NOT_FOUND: /models/models.config; No such device"

This error message is from the Docker Log for:
semantic-search-main-tf-serving-1 tensorflow/serving:latest

Also upon inspection models has only 3 empty folders with no files.