Gyanendra Sinha
Gyanendra Sinha
Link to landed trunk PR: - https://github.com/pytorch/executorch/pull/2984 Link to release branch PR: - https://github.com/pytorch/executorch/pull/3134 Criteria category and reasons: - The PR has fixes for running the llama model using the...
Link to landed trunk PR: - https://github.com/pytorch/executorch/pull/2975 Link to release branch PR: - https://github.com/pytorch/executorch/pull/3157 Criteria category and reasons: - coremltools has support for Index_Put operation and there is no need...
@orgicus thus could be a path issue, could you please check the name of the cloned directory, if the name is not executorch then please rename it to executorch.
@ITHelpDec are you trying to build the `main` or `stable` branch? If `main` could you please pull the latest changes and try again?
@YifanShenSZ is this still an issue?
Thanks for the fix @billmguo! could you please add unit tests?
@plumenator could you please share a reproducible example?
@junpeiz could you please take a look?
@MusickMe could you please try to export the model as an `ML Program`? ```python model = ct.convert( source_model, convert_to="mlprogram", compute_precision=ct.precision.FLOAT32) ```
@maxW2000 the error indicates that there is a shape mismatch. The model that you are exporting has fixed input shapes, could you please try converting with flexible inputs https://apple.github.io/coremltools/docs-guides/source/flexible-inputs.html#set-the-range-for-each-dimension