Digant Desai
Digant Desai
Inappropriate detection of dynamic dimensions in executorch/backends/xnnpack/operators/op_squeeze.py
Fixed.
We just updated it to not-so-latest [commit](https://github.com/digantdesai/XNNPACK/tree/4ea82e595b36106653175dcb04b2aa532660d0d8) (3 weeks old) with PR #139913 😞 Let's see what we can do. cc @mcr229
We need to update xnnpack submodule, the fix upstream has landed.
CI issues?
Can't tell why the arm-backend job is failing, seems like infra issue, because FVP returned 0. Let me rerun it.
still failing with `executorch/backends/arm/operators/op_reciprocal.py:44:46 Incompatible parameter type [6]`
Also rebase when you fix this 😓
> Data layout ops like unsqueeze are not annotated by the quantizer per default which leads to issues down the line Can you elaborate? what issues? Is it just lowering...
Please rebase?
Internal checker found these type issues, can you please fix and rebase? Thanks. ``` Found type errors! executorch/backends/arm/tosa_utils.py:356:16 Undefined or invalid type [11]: Annotation `torch.tensor` is not defined as a...