[cadence][hifi] Fix cadence backend example for i.MXRT600#18872
[cadence][hifi] Fix cadence backend example for i.MXRT600#18872robert-kalmar wants to merge 1 commit intopytorch:mainfrom
Conversation
Fixing the build of the cadence backend example for i.MXRT600. Guideline updated to reference a particular NXP MCUXpresso SDK (25.12) and added selective kernel registration, based on model used as the full executorch op library exceeds the i.MXRT600 memory.
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18872
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 1 Awaiting Approval, 2 New Failures, 2 Cancelled JobsAs of commit 6774d7c with merge base 36e8ed9 ( NEW FAILURES - The following jobs have failed:
CANCELLED JOBS - The following jobs were cancelled. Please retry:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This PR needs a
|
|
@mcremon-meta, as per discussion on #16898 filing this draft PR which fixes the build of the Cadence example in ExecuTorch. Not yet ready to be merged, as need to verify the example on i.MXRT600. |
Summary
Fixing the build of the cadence backend example for i.MXRT600. Guideline updated to reference a particular NXP MCUXpresso SDK (25.12) and added selective kernel registration, based on model used as the full executorch op library exceeds the i.MXRT600 memory.
Fixes #16898
Test plan
TBD.
CC @mcremon-meta , @jirioc , @aliafzal