[Feature Request] Universal cache invalidation

[henryruhs]

Describe the feature request

From my research only TensorRT has proper cache invalidation, once onnxruntime has been updated the outdated caches are causing onnxruntime to crash.

EP	Auto-invalidation	Version Detection
TensorRT (ORT 1.20+)	Yes	Runtime
MIGraphX	Partial	Compile-time
CoreML	No	None

For now I use this workaround.

import os
import onnxruntime

cache_path = os.path.join('.caches', onnxruntime.get_version_string())

session = onnxruntime.InferenceSession('model.onnx', providers = [('CoreMLExecutionProvider',
{
	'ModelCacheDirectory': cache_path
})])

Describe scenario use case

I recommend a universal solution to handle caches, it should not be EP specific.