executorch

executorch copied to clipboard

update gihub links to release/0.2 branch

1

Summary: In readme of alpha github, some links are pointing to stable or main branch github repostory. However, for alpha release, we need to make sure those links are also...

Gasoonjia

load_method with only method name

3

Running the tutorial https://pytorch.org/executorch/stable/running-a-model-cpp-tutorial.html I got error `error: too few arguments to function call expected at least 2, have 1 Result method = program->load_method(method_name);` I've created model with variable shape...

victoriapoghosian

build of executorch triggers a warning related to too many arguments provided for format string. https://github.com/pytorch/torchchat/actions/runs/8768143958/job/24062159094?pr=327 ``` In file included from /home/runner/work/torchchat/torchchat/etorch/executorch/extension/data_loader/../../../executorch/runtime/core/error.h:18, from /home/runner/work/torchchat/torchchat/etorch/executorch/extension/data_loader/../../../executorch/runtime/core/result.h:19, from /home/runner/work/torchchat/torchchat/etorch/executorch/extension/data_loader/../../../executorch/runtime/core/data_loader.h:14, from /home/runner/work/torchchat/torchchat/etorch/executorch/extension/data_loader/../../../executorch/extension/data_loader/mmap_data_loader.h:11, from /home/runner/work/torchchat/torchchat/etorch/executorch/extension/data_loader/mmap_data_loader.cpp:9:...

mikekgfb

fix lint

3

Differential Revision: D56390653

cccclai

conv1d with bias=False

2

Summary: Under the same setting as the last diff, we support `bias=false`. Differential Revision: D56285842

copyrightly

Add exportable Wav2Vec2ASR model

2

Summary: With this change, Wav2Vec2ASR can be lowered. Note that is cannot run yet, because it is missing many ops. Differential Revision: D56377662

mcremon-meta

Update setup.sh for tokenizer selection

4

Summary: For LLAMA3, users need to use tiktoken. Add a option to load from env var. Differential Revision: D56374673

kirklandsign

conv1d

1

Summary: We follow D50914117 to implement a specific case of conv1d for our needs. Specifically, we require - the input tensor to have a single batch - groups == in_channels...

copyrightly

make op_split_with_sizes_copy support dynamic shape

1

Summary: as title Reviewed By: SS-JIA Differential Revision: D56333587

pytorchbot

[QNN] Support non-Android aarch64 Linux targets for QNN backend?

1

I'm targeting Snapdragon 8 Gen 2 hardware, but it is using (non-Android) aarch64 Linux (under a QNX hypervisor) as the operating system. I've been able to use the QNN SDK...

tc-wolf