tflite: mtk_neuron: Reject AsymI16 quantization on MT8188 MDLA According to the document, MT8188 MDLA does not support AsymI16 operations. Therefore, we should reject such operations if encountered. Note that MT8196 MDLA does support it, so we should check for the platform here. BUG=b:338959718 TEST=cros_sdk tast run $CIRI_DUT 'tflite.DTS.neuron' Change-Id: Ic0402060cb3f70a7d922b9cd4d1905117d92fc75 Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/tflite/+/6275669 Auto-Submit: Tommy Chiang <ototot@google.com> Tested-by: Tommy Chiang <ototot@google.com> Reviewed-by: Shik Chen <shik@chromium.org> Commit-Queue: ChromeOS Auto Retry <chromeos-auto-retry@chromeos-bot.iam.gserviceaccount.com>
This repository hosts the core ChromeOS TFLite components, enabling on-device machine learning (ODML) workloads accelerated by NPU.
The corresponding ebuild can be found at: tensorflow-9999.ebuild
Patches are stored in the patch/ directory and explicitly listed in WORKSPACE.bazel. A helper script, ./script/patcher.py, is included to facilitate patch management within a TFLite workspace.
The typical workflow:
Eject (Download) TensorFlow Source Code
Download the TensorFlow source code into a local git repository with patches applied as individual commits:
./script/patcher.py eject
This creates a new local git repository at tensorflow/.
Modify the TensorFlow Repository
Make changes to the tensorflow/ repository as needed, following standard git workflows. Optionally, include a PATCH_NAME= tag in commit messages to specify the filename of the corresponding patch.
Seal the Repository
Regenerate the patch files and update the WORKSPACE.bazel file:
./script/patcher.py seal
This updates the patches in the patch/ directory and reflects the changes in WORKSPACE.bazel.
It's preferred to submit changes to upstream TensorFlow first and cherry-pick them as patches. This helps minimize divergence and makes TensorFlow updates easier.