Add support for converting DLTensor for NPU device type #14878
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR extends dlpack convertor in onnxruntime to support DLDeviceType::kDLExtDev for NPU device type.
Motivation and Context
ORT InferenceSession (used for ORTModule and DORT) produces results as ortvalue, and convert them to at Tensor through dlpack. Currently, it supports converting tensors for CPU and GPU. This PR adds support for the conversion for NPU ORT device type between
DLTensorand ORT tensor for NPU device type. Currently in the PR, tensor conversion through DLPack borrows DLExtDevice, which is planned to use DLOrt once a PR that supports DLOrt is merged.Related PR in pytorch for the conversion between DLTensor and at Tensor for ORT NPU device type: pytorch/pytorch#95859