[CompilerPlugin] Google Tensor

[wubba1337]

Hi, @leeroyka
Apologize for the delayed response, Thanks for filing this issue. Currently, LiteRT in Google Play Services C/C++ only provides the GPU and XNNPACK delegates at the moment. NNAPI has been deprecated as of Android 15 please refer this official documentation There’s no NNAPI delegate in the Play Services package.

NPU support is limited to Qualcomm AI Engine devices. Google Pixel Tensor delegate is coming in the coming months (Please refer this official documentation) and via the experimental Tensor ML SDK (sign up at https://ai.google.dev/edge/litert/next/tensor_ml_sdk). In the meantime, please use the GPU delegate (gpu_plugin.h) for acceleration. Thank you for your cooperation and patience.

Originally posted by @gaikwadrahul8 in #3936

Hi, just wondering if there would be an update for Google Pixel Tensor delegate? I've sign up for the experimental Tensor ML SDK and would be interested in using it. Thank you.

[sourcelite]

Welcome here and thankyou for signing up for experimental Tensor ML SDK.

As of now the status is coming soon. I recommend you to do watch at the space for official announcements regarding Google Pixel Tensor delegate - https://ai.google.dev/edge/litert/android/npu/overview. Thanks!

[github-actions]

Marking this issue as stale since it has been open for 7 days with no activity. This issue will be closed if no further activity occurs.

[Quackdoc]

bumping for the bot

[wubba1337]

Will wait for the release. Closing this issue.