executorch
executorch copied to clipboard
pytorch
On-device AI across mobile, embedded and edge for PyTorch
Summary: Pull Request resolved: https://github.com/pytorch/executorch/pull/3260 As title, the link was wrong... Reviewed By: kirklandsign Differential Revision: D56498322 fbshipit-source-id: 42708b5f7a634f1c01e05af4c897d0c6da54d724 (cherry picked from commit e9d7868abd2e5cd9aa5b6e91c5dc22ed757cc0bd)
### Summary - Support static kv_cached llama2 model - We reference AIMET jupyter notebooks and implement a [static LLAMA](https://github.com/CodeLinaro/executorch/blob/9681c0195a17952a95042c407d4d01e4e2b4bab1/examples/qualcomm/llama2/model/static_llama.py) - Add [qnn_llama_runner](https://github.com/CodeLinaro/executorch/blob/9681c0195a17952a95042c407d4d01e4e2b4bab1/examples/qualcomm/executor_runner/qnn_llama_runner.cpp) to run static LLAMA - Add [e2e example...
Summary: There are use cases where we might like to supply a separate ExecutorchBackendConfig for each method in the model. An example use case is where we might want to...
Right now we are not building it and it is causing missing ops in torchchat. This PR adds it into pybinding.
I'm working on https://github.com/pytorch/executorch/issues/1759 and open this one for testing.
Can the pte file generated by executorch be tested directly in the python virtual environment? If possible, how can I use my own data set to test?
Would it be possible to enhance the existing memory planner to cover situations where intelligent use of memory offsets can eliminate unnecessary copies? I am posting a minimal example below:...
Summary: Noticed this overflow when I was looking through the XNNPACK backend. I am not very familiar with executorch or XNNPACK, so please be critical in review! In particular, my...
Summary: IIUC, this README is describing the entire kernels/ subtree, not kernels/portable. Move it and leave a breadcrumb in its old location. Differential Revision: D56494181
