Adding a GPU model to the compatibility database in tflite

[hooneecho]

Issue type

Support

Have you reproduced the bug with TensorFlow Nightly?

No

Source

source

TensorFlow version

tf2.15

Custom code

Yes

OS platform and distribution

No response

Mobile device

No response

Python version

No response

Bazel version

No response

GCC/compiler version

No response

CUDA/cuDNN version

No response

GPU model and memory

No response

Current behavior?

I have a question in the "acceleration/compatibility" part in tflite.
As far as I know, Samsung mobile model "samsung_xclipse_920" (S22) information was recently added to the compatibility database to check and support the GPU delegation.
1f3d148

I would like to add "samsung_xclipse_940", a S24 model that was recently released officially on the market,
Are there any ways to do it? Is there anything already in progress? Or, can I upload some PRs (gpu_compatibility.bin ...) related to this manually?

Standalone code to reproduce the issue

flatc -t --raw-binary --strict-json database.fbs -- gpu_compatibility.bin
flatc -b database.fbs gpu_compatibility.json

Relevant log output

No response

[pkgoogle]

Hi @rubber815, there is probably a way ... @impjdi, can you please take a look? Thanks.

[ElonGreco]

Hi @impjdi ,
I would like to know how to submit GPU model information to the compatibility database in tflite? Thanks.

[gaikwadrahul8]

Hi, @hooneecho
Thanks for raising this issue. Are you aware of the migration to LiteRT? This transition is aimed at enhancing our project's capabilities and providing improved support and focus for our users. As we believe this issue is still relevant to LiteRT we are moving your issue there. Please follow progress here: google-ai-edge/LiteRT#76

Let us know if you have any questions. Thanks.

[google-ml-butler]

Are you satisfied with the resolution of your issue?
Yes
No