Manas Mohanty

Closing this issue as concerned PR has been merged. Thank you!

Hi @aflaischer @nyadla-sys ! Thanks for confirming the same and providing your inputs. It would be great to have a PR from your side to update the CMake documentation to...

@gbaned Gentle bump on merging the PR. Changes has not reflected in master branch yet. Thank you!

Yes @renatobellotti ! I can confirm that workarounds are not working for sparse-dense multiplication in GPU mode. Attached gist in [2.8](https://colab.sandbox.google.com/gist/mohantym/94eef9660238c07f2b0b600d9a2fe5df/git_56547.ipynb#scrollTo=ou1eAMNWxFjp), [2.9](https://colab.sandbox.google.com/gist/mohantym/06ccb760628d6af6b21d835a50fc9165/git_56547.ipynb#scrollTo=WB-45fTlxRyn) and [nightly](https://colab.sandbox.google.com/gist/mohantym/31be331038a45eea092b531ffd59380e/git_56547.ipynb#scrollTo=WB-45fTlxRyn) for reference. Thank you!

Hi @twerkmeister ! Thanks for sharing your observation on installing Tensorflow 2.11 on Windows through poetry. @SuryanarayanaY ! Could you look at this issue. Thank you!

@StuartIanNaylor ! Thanks for sharing your observation w.r.to inference timing on tflite_runtime and tf.lite.runtime and OpenAi whisper model. I see the results in above comments are pretty close considering the...

@StuartIanNaylor ! Thanks for the clarification. For Arm Specific implementation , You can create custom TFLite Runtime through Cross compiling through CMake and flags mentioned [here](https://www.tensorflow.org/lite/guide/build_cmake#available_options_to_build_tensorflow_lite) for different delegate support....

Hi @pavanimajety ! It seems you are using older versions(1.x versions) of Tensorflow which is not supported any more. Could you confirm whether issue is replicating after [migrating](https://www.tensorflow.org/guide/migrate/migrate_tf2) to versions...

@pavanimajety ! I could not replicate the issue with [2.11. ](https://colab.sandbox.google.com/gist/mohantym/c4d47265162f0e92313e598cb8104848/git_59117.ipynb#scrollTo=EZyEQtaLasRG) Could you try with 2.11 , Cuda 11.2 and Cudnn 8.1 and let us know. Thank you!

@pavanimajety ! Thanks for the update. @SuryanarayanaY ! Could you look at this issue. Thank you!