NXP backend: switch from raw tflite to from ir.lib.tflite#17548
Conversation
Summary: Following convention, do not use from tflite but rather the lib in Executorch backend, eg from executorch.backends.nxp.backend.ir.lib.tflite.BuiltinOperator import BuiltinOperator This allows for usage in environments where tflite is not installed. Reviewed By: SS-JIA Differential Revision: D93624349
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17548
Note: Links to docs will display an error until the docs builds have been completed. ❌ 6 New Failures, 1 Unrelated FailureAs of commit 688c120 with merge base 7caf9b2 ( NEW FAILURES - The following jobs have failed:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
@JakeStevens has exported this pull request. If you are a Meta employee, you can view the originating Diff in D93624349. |
SS-JIA
left a comment
There was a problem hiding this comment.
Review automatically exported from Phabricator review in Meta.
This PR needs a
|
|
NXP failure pre existing and un related, see Has same. |
We're looking into it. |
Summary:
Following convention, do not use from tflite but rather the lib in Executorch backend, eg
from executorch.backends.nxp.backend.ir.lib.tflite.BuiltinOperator import BuiltinOperator
This allows for usage in environments where tflite is not installed.
Reviewed By: SS-JIA
Differential Revision: D93624349
cc @robert-kalmar @digantdesai