| commit | a964217d52f816b7c55e4222f11ce5d38e21f248 | [log] [tgz] |
|---|---|---|
| author | Tommy Chiang <ototot@chromium.org> | Tue Apr 08 21:35:30 2025 |
| committer | Chromeos LUCI <chromeos-scoped@luci-project-accounts.iam.gserviceaccount.com> | Thu Jun 12 10:59:36 2025 |
| tree | 89b534faea830c356850f7c8cf801df2d1fa1388 | |
| parent | d78d3c831e5a95cbcb9f6df444a018ef22b678fd [diff] |
tflite: mtk_neuron: Add AbortedWhenWaiting test According to MTK's document, the abort time consider both model inference time and waiting time. This CL check if this is true by sending a large model to block the NPU and send a small model with a slightly larger abort time. The expected behavior is the small model will be aborted in the given time frame, without needing to wait the large model complete its work. BUG=b:374245241 TEST=neuron_delegate_test on navi Change-Id: Ifc3503765e5337e16417deb61f9346d486747f02 Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/tflite/+/6437797 Reviewed-by: Shik Chen <shik@chromium.org> Commit-Queue: Tommy Chiang <ototot@google.com> Tested-by: Tommy Chiang <ototot@google.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.