Zingo Andersen

Seem to be timeout, rerun test to check

Seem to be happening after https://github.com/pytorch/executorch/pull/14109 was merged, trying to revert that PR

Rebased after problem PR was reverted

Timeout again :( [trunk / test-arm-backend (test_pytest_ops_ethosu_fvp) / linux-job (push)](https://github.com/pytorch/executorch/actions/runs/19367891399/job/55415753214?pr=15828)Cancelled after ...

Seem to be happening after https://github.com/pytorch/executorch/pull/14109 was merged, trying to revert that PR

Nope that is correct, the example just allocates a 60MB buffer so we can test/used large models out of the box as the FVP can use quite much memory. See...

This might be a longshot but there is something called selective build type, I have not checked it out at all but it might be something that brings your size...

As a fast CI fix I created this pull request https://github.com/pytorch/executorch/pull/5843 until this is sorted out

Hi after the merge of: Add sigmoid to one-to-one annotator in ArmQuantizer (https://github.com/pytorch/executorch/pull/6047) We are ready to close this (from Arm side of things) @Jack-Khuu & @digantdesai is there anything...

I just got a extra PEI sheet from a another brand and my eddy calibration was trown off :( It would be interesting to see if the "Tap" you do...