* fix image to image for coreml
* fix image to image for coreml
* Update metadata.py
* modernize onnxruntime
* introduce cuda@12 and cuda@13 for installer
* introduce cuda@12 and cuda@13 for installer
* temporary fix for inference pool disaster
* temporary fix for inference pool disaster
* use onnxruntime 1.24.4 for cuda@12
* fix test
* fix test
* fix test
* add test for job list
* switch to has_arena_leak guard
* remove directml hack for inference pool
* uninstall every onnxruntime first
* uninstall every onnxruntime first
* restore the directml fix
* restore the directml fix
* fix directml again
* simplify condition