Fix AutoAWQQuantizer GptqQuantizer supported ep and device

[xiaoyu-work]

Describe your changes

Fix AutoAWQQuantizer GptqQuantizer supported ep and device.

Checklist before requesting a review

• Add unit tests for this change.
• Make sure all tests can pass.
• Update documents if necessary.
• Lint and apply fixes to your code by running lintrunner -a
• Is this a user-facing change? If yes, give a description of this change to be included in the release notes.
• Is this PR including examples changes? If yes, please remember to update example documentation in a follow-up PR.

(Optional) Issue link

[jambayk]

maybe we should make it * for both providers and ep. the quantization happens on pytorch model and the exported model is compatible with all eps.

[jambayk]

their only requirement is that they require gpus to run. but that is a host machine requirement, not target provider or ep.

[xiaoyu-work]

Does this supported_providers mean the output model supports which ep? Same concept for supported_accelerators?

[jambayk]

yes. it's used by the auto-opt to filter out the passes based on the intended target ep

[xiaoyu-work]

I see. I can see some other passes like QNNConversion is also in this list. But QNN model doesn't not have any ep concept. If this is only used by auto-opt, and auto-opt is targeting onnx model, should those unrelated pass whose output model is not onnx model be removed here?

[jambayk]

@shaahji can comment more on it. I think in general, we can just use * for passes that don't deal with onnx models. that way if they are scheduled by the auto-opt, they don't get filtered out.