executorch
executorch copied to clipboard
pytorch
On-device AI across mobile, embedded and edge for PyTorch
Revert https://github.com/pytorch/executorch/pull/4101
Summary: Adding `GEMMConfig(XNNPartitionerConfig)` This is a base class which handles grabbing all the dependencies of a gemm like node (conv, addmm, linear) and then validates that the node is a...
This draft has some overlapped parts with https://github.com/pytorch/executorch/pull/4163 in order to demo use case. For key changes, please check files under `exir`, `runtime/executor`, `schema`.
Summary: Implement aten.meshgrid.default with 2 input tensors. This op is compiled from [torch.meshgrid](https://pytorch.org/docs/stable/generated/torch.meshgrid.html#torch-meshgrid). Also add it into `ops_not_to_decompose`, otherwise it will be decomposed to several ops. Test can be found...
### 🐛 Describe the bug I encountered a segmentation fault when implementing llama/stories110M Android phone deployment according to the #https://github.com/pytorch/executorch/blob/main/examples/models/llama2/README.md. I put xnnpack_stories110M.pte, tokenizer.bin and llama_main compiled with xnn backend...
### 🐛 Describe the bug Hello, I'm trying to compile and run some models for Executorch with QCOM backend, but I've bumped into various issues at build & execution time....
> Please provide a brief reason on why you need to mark this job as unstable. ET doesn't currently support python 3.9
> Please provide a brief reason on why you need to mark this job as unstable. ET doesn't currently support python 3.9
Summary: The decomposition from ``` class IndexPut(torch.nn.Module): def __init__(self): super().__init__() def forward(self, x, input_pos, value): x[:, :, input_pos] = value return x ``` is ``` opcode name target args kwargs...
