pytorch/executorch

View on GitHub

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

Stars: 5k
Forks: 1.2k
Open beginner issues: 0
Indexed issues: 851
Avg merge: 2d 10h
Merged PRs (30d): 581

Dominant language: Python
License: No license data
Last GitHub push: Sep 20, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: good first issue help wanted

Beginner friendly Everything

Open All

851 open issues indexed

Running Qwen3 in Android LlamaDemo App shows an error while loading tokenizer Open

module: android module: examples

pytorch/executorch#11311 · 8 comments · 1 reaction · 1 assignee · Opened Jun 3, 2025
Cmake selective build: add wrapper for the three APIs. Open

module: build/install

pytorch/executorch#11296 · 1 assignee · Opened Jun 2, 2025
torchao build fails on macOS arm64 due to missing symbol c10::StorageImpl::throw_data_ptr_access_error() Open

pytorch/executorch#11283 · 2 comments · 2 assignees · Opened Jun 2, 2025
Include Xcode in our macOS runners Open

module: build/install

pytorch/executorch#11272 · 1 assignee · Opened May 30, 2025
Manual kernel registration to include library names in API Open

good first issue module: runtime

Difficulty 4/5 3-5 days Newbie friendliness 45/100

pytorch/executorch#11221 · 6 comments · 2 reactions · Opened May 29, 2025
Qwen3-0.6B QNN Execute Error Open

module: qnn partner: qualcomm

pytorch/executorch#11213 · 6 comments · 1 assignee · Opened May 29, 2025
Include ClangCL toolset in MSVC Open

module: build/install

pytorch/executorch#11199 · 5 comments · 2 reactions · 2 assignees · Opened May 28, 2025
No module named 'pytorch_tokenizers' Open

pytorch/executorch#11180 · 1 comment · 1 assignee · Opened May 28, 2025
Why are models like Llama implemented again in examples/models/ ? Open

module: examples triaged

Difficulty 5/5 Over a week Newbie friendliness 25/100

pytorch/executorch#11130 · 5 comments · Opened May 26, 2025
[Request help] Can't add new parameters to the kernel generated by 6x16-aarch64-neonfp16arith-cortex-a75.S.in Open

module: xnnpack triaged

pytorch/executorch#11098 · 3 comments · 1 assignee · Opened May 23, 2025
Ops with included input dim order conversion fail at runtime Open

module: exir

Difficulty 4/5 3-5 days Newbie friendliness 48/100

pytorch/executorch#11086 · 5 comments · Opened May 23, 2025
Issue with run the Cadence demo on Ubuntu 22.04 Open

module: cadence triaged

pytorch/executorch#11050 · 8 comments · 1 assignee · Opened May 21, 2025
Quantized model repository for different backends Open

module: llm triaged

pytorch/executorch#11034 · 7 comments · 1 assignee · Opened May 21, 2025
Quantization of Llama3.2-1b/3b with QNN backend Open

module: qnn triaged

pytorch/executorch#10993 · 5 comments · 1 assignee · Opened May 20, 2025
armv8-2a-qcom-linux Cross compilation flatc issue Open

module: build/install triaged

pytorch/executorch#10964 · 5 comments · 1 assignee · Opened May 19, 2025
Request for qwen_2.5-omni-3B deploying with xnnpack backend Open

module: examples

Difficulty 5/5 Over a week Newbie friendliness 25/100

pytorch/executorch#10937 · 2 comments · Opened May 16, 2025
Re-inplace slice_copy with slice Open

good first issue

pytorch/executorch#10917 · 7 comments · 1 reaction · 1 assignee · Opened May 15, 2025
[QCOM] [Llama] Gibberish Result on Llama 3.2 1B Open

module: qnn partner: qualcomm

Difficulty 4/5 3-5 days Newbie friendliness 25/100

pytorch/executorch#10900 · 4 comments · Opened May 15, 2025
cyclic dependency while executing the example/arm/setup.sh Open

module: build/install partner: arm

pytorch/executorch#10899 · 5 comments · 1 assignee · Opened May 15, 2025
Build qwen3 with qnn backend fails Open

module: qnn partner: qualcomm

Difficulty 4/5 3-5 days Newbie friendliness 25/100

pytorch/executorch#10895 · 4 comments · Opened May 15, 2025
Remove the PyTorch Moble iOS and Android folders Open

module: doc

pytorch/executorch#10894 · 1 comment · 1 assignee · Opened May 15, 2025
[Android] Rename JNI cpp file Open

good first issue module: android triaged

Difficulty 2/5 1-3 hours Newbie friendliness 45/100

pytorch/executorch#10890 · 3 comments · Opened May 15, 2025
Develop ET Server Binary + Distribute Prebuilt Releases via GH? Open

module: examples

Difficulty 5/5 Over a week Newbie friendliness 20/100

pytorch/executorch#10888 · 1 comment · Opened May 15, 2025
Get rid of fixed number cmake --build -j in sh and docs Open

good first issue module: build/install triaged

Difficulty 3/5 1-2 days Newbie friendliness 48/100

pytorch/executorch#10887 · 3 comments · 1 reaction · Opened May 14, 2025
iOS Llama demo app segfaults if the tokenizer file is malformed Open

pytorch/executorch#10879 · 1 assignee · Opened May 14, 2025
iOS Llama Demo App crashes if it doesn't like the PTE name Open

module: ios module: llm

pytorch/executorch#10876 · 1 comment · 1 assignee · Opened May 14, 2025
Automatically specify params and metadata for export LLM Open

module: llm

pytorch/executorch#10862 · 1 assignee · Opened May 13, 2025
Allow loading downstream HF repos Open

module: llm

pytorch/executorch#10861 · 1 assignee · Opened May 13, 2025
Out-variant kernels are lacking BC protection for new default args being added. Open

module: runtime

pytorch/executorch#10821 · 1 assignee · Opened May 12, 2025
Consolidate executor_runners Open

good first issue module: build/install

Difficulty 4/5 3-5 days Newbie friendliness 48/100

pytorch/executorch#10819 · 5 comments · Opened May 12, 2025
Create a landing page for executorch mobile Open

module: user experience triaged

pytorch/executorch#10796 · 3 comments · 1 assignee · Opened May 9, 2025
Remove all instances and usages of torchscript Open

module: user experience triaged

pytorch/executorch#10795 · 1 comment · 1 assignee · Opened May 9, 2025
Add timestamps for pte generation in CI Open

good first issue module: ci triaged

pytorch/executorch#10761 · 7 comments · 1 assignee · Opened May 7, 2025
Deploying VITA-1.5 Multimodal Model with ExecuTorch Open

module: llm triaged

Difficulty 5/5 Over a week Newbie friendliness 20/100

pytorch/executorch#10757 · 7 comments · Opened May 7, 2025
[CMake] Duplicated sources in extension_llm_runner and llama_runner Open

module: build/install triaged

pytorch/executorch#10746 · 1 assignee · Opened May 7, 2025
Make debug handle as first citizen of Export Graph Open

module: devtools triaged

pytorch/executorch#10728 · 1 assignee · Opened May 6, 2025
Consolidate debug handle infra from Export Graph, torch.ao to ExecuTorch Open

module: devtools triaged

pytorch/executorch#10727 · 1 assignee · Opened May 6, 2025
Python runtime API for operators Open

module: runtime triaged

Difficulty 5/5 Over a week Newbie friendliness 35/100

pytorch/executorch#10726 · Opened May 6, 2025
_load_for_executorch_from_buffer doesn't keep buffer alive Open

module: extension triaged

Difficulty 4/5 3-5 days Newbie friendliness 35/100

pytorch/executorch#10725 · Opened May 6, 2025
[Neutron Backend] Move Neutron Backend to Dim Order Representation usage Open

module: nxp triaged

pytorch/executorch#10711 · 2 comments · 1 reaction · 2 assignees · Opened May 6, 2025
[CMake] Decouple prim_ops from executorch Open

module: build/install triaged

pytorch/executorch#10704 · 1 comment · 3 assignees · Opened May 6, 2025
Add torchao kernels to xcframework Open

good first issue module: build/install module: ios module: quantization triaged

pytorch/executorch#10694 · 2 comments · 1 reaction · 1 assignee · Opened May 5, 2025
[CMake] Duplicated entries in executorch_srcs.cmake Open

module: build/install triaged

pytorch/executorch#10687 · 1 comment · 3 assignees · Opened May 5, 2025
[CMake] Potentially duplicated srcs in llama_runner build Open

good first issue module: build/install triaged

pytorch/executorch#10686 · 3 assignees · Opened May 5, 2025
[CMake] Enable BUILD_SHARED_LIBS=ON flag Open

module: build/install triaged

Difficulty 4/5 3-5 days Newbie friendliness 30/100

pytorch/executorch#10676 · Opened May 4, 2025
Support selective build for Android Open

module: android

pytorch/executorch#10622 · 2 comments · 1 reaction · 1 assignee · Opened May 1, 2025
Question about programmatically running inference on Android-based custom OS with vulkan delegate Open

module: vulkan

Difficulty 4/5 3-5 days Newbie friendliness 25/100

pytorch/executorch#10602 · 10 comments · Opened May 1, 2025
Advice on how to run the training example in Android Open

module: android module: training

Difficulty 5/5 Over a week Newbie friendliness 20/100

pytorch/executorch#10593 · 9 comments · Opened Apr 30, 2025
Need a feature to get etdump while running LLAMA model on qnn with qnn_llama_runner Open

good first issue module: qnn

Difficulty 4/5 3-5 days Newbie friendliness 45/100

pytorch/executorch#10580 · 3 comments · Opened Apr 30, 2025
runtime oeprator-level numeric issue detector Open

pytorch/executorch#10554 · 1 assignee · Opened Apr 29, 2025

pytorch/executorch

Get new issues in your inbox