pytorch/executorch

XNNPACK Buck build appears not to enable KleidiAI/SME2 while CMake enables KleidiAI by default 1 day ago

help wanted module: xnnpack partner: arm

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

insert_write_back_for_buffers_pass should inject copy_ nodes at the earliest possible spot. 2 days ago

good first issue module: exir triaged

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Good First Issue: Runtime MoE expert-sort for decode (MLX backend, Qwen 3.5 MoE) 7 days ago

good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

[MLX][Good first issue] Add Q5K quantization support 8 days ago

good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Optimized linear op doesn't support bias 10 days ago

enhancement good first issue actionable module: kernels triaged

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Good First Issue: top-k filtering for `mlx::sample` (MLX backend) 11 days ago

good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Good First Issue: isolate the MLX submodule build (MLX backend) 12 days ago

good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

[MLX] Good First Issue: Skip MoE expert sorting during decode (MLX backend, Qwen 3.5 MoE) 19 days ago

good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

# Good First Issue: In-Model Sampling Head for the MLX Backend (Gumbel Sampling) 21 days ago

good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

[Good first issue] Add Q4K support to MLX backend 28 days ago

good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Add Android model E2E test about 1 month ago

good first issue module: android

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Python apis for loading and saving .ptd from dictionaries about 1 month ago

good first issue triaged module: training

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Good First Issue: Add MLX Op Handler for aten.flip about 2 months ago

good first issue triaged

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Consolidation of Selective Build APIs for OSS about 2 months ago

good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Outdated versions in links on ET Doc page 2 months ago

module: doc good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Content changes required in Doc page 2 months ago

module: doc good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Good First Issue: Enable Gemma 4 on MLX Backend 3 months ago

good first issue triaged

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Good First Issue: Add MLX Op Handler for `aten.roll` 3 months ago

good first issue triaged

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Good First Issue: Add MLX Op Handler for `aten.trunc` 3 months ago

good first issue triaged

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Good First Issue: Add Full Integer Support for `aten.bitwise_not` 3 months ago

good first issue triaged

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Good First Issue: Add Full Integer Support for `aten.bitwise_and` 3 months ago

good first issue triaged

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Good First Issue: Add MLX Op Handler for `aten.bitwise_xor` 3 months ago

good first issue triaged

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Good First Issue: Add MLX Op Handler for `aten.bitwise_or` 3 months ago

good first issue triaged

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Good First Issue: Add MLX Op Handler for `aten.isinf` 3 months ago

good first issue triaged

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Good First Issue: Add MLX Op Handler for `aten.isnan` 3 months ago

good first issue triaged

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Good First Issue: Add MLX Op Handler for `aten.hardtanh` 3 months ago

good first issue triaged

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Clean up pytest warnings 4 months ago

good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Support dim order in Java Tensor 4 months ago

good first issue module: android

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

[Android] instrumentation test use models from storage, not bundled with apk 4 months ago

good first issue triaged module: android

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

[Android] Rename JNI cpp file 4 months ago

good first issue triaged module: android

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Remove the outdated warning in building from source documentation 5 months ago

module: doc good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Add test to ensure scalar_type.fbs remains in sync across the executorch repo 5 months ago

good first issue module: exir

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Add warning when users use to_edge instead of to_edge_transform_and_lower with CoreML 5 months ago

good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Re-inplace slice_copy with slice 7 months ago

good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Support Standalone Batch Norm 7 months ago

good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Add timestamps for pte generation in CI 8 months ago

good first issue module: ci triaged

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Zeros/Ones Tensor Constructor (Android) 8 months ago

good first issue module: android

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

[Arm] Size-test: Run the binary on CI 10 months ago

good first issue actionable module: arm

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Add dim order variant clone operator 10 months ago

good first issue actionable module: exir

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Fail to allocate temp memory by exporting torch.topk 10 months ago

good first issue module: runtime triaged

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

[Android] Add method metadata report API in Module.java 11 months ago

good first issue triaged module: android Android_GA

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

[Android] Add a Runtime.java 11 months ago

good first issue triaged module: android Android_GA

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Add pybindings for text LLM runner 12 months ago

AI Summary: The task involves creating Python bindings for a C++ API within the ExecuTorch project, specifically for its text LLM runner. This requires writing a pybind11 C++ file, integrating it into the existing CMake build system, adding the module to setup.py, and ensuring compatibility with existing .pte files and tokenizer artifacts. The goal is to allow users to run LLM models within a Python environment, such as a Jupyter notebook.

Complexity: 4/5

good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

sym_max support in ExecuTorch about 1 year ago

AI Summary: Implement support for the `sym_max` operation within the ExecuTorch framework. This is necessary to enable successful graph lowering and model execution for models utilizing dynamic cache sizes, as highlighted by an issue encountered in the `optimum-executorch` project when exporting models from the Hugging Face Transformers library.

Complexity: 4/5

good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Rename `executorch` cmake target to `prim_ops_lib` about 1 year ago

AI Summary: Rename the CMake target `executorch` to `prim_ops_lib` in the ExecuTorch project to improve clarity and consistency with other libraries. This involves updating the CMakeLists.txt file and potentially `executorch-config.cmake` to reflect the name change and remove redundant linking code in example projects.

Complexity: 3/5

good first issue

pytorch/executorch

4.8K

On-device AI across mobile, embedded and edge for PyTorch

Python

#deep-learning#embedded#gpu#machine-learning#mobile#neural-network#tensor

Open Issues Need Help