Intel GPU support

[mudler]

Is your feature request related to a problem? Please describe.

While Intel GPUs acceleration is partially supported with llama.cpp , https://github.com/intel/intel-extension-for-transformers seems to be specifically optimized to run optimized flow for intel.

For example, to run SD: https://www.intel.com/content/www/us/en/developer/articles/technical/stable-diffusion-with-intel-arc-gpus.html

Describe the solution you'd like

Support for
https://github.com/intel/intel-extension-for-transformers

Describe alternatives you've considered

Additional context

[mudler]

#1660
#1689
#1686