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

Continuous coverage and performance monitoring of GA models for CoreML backend. Open

triaged

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

pytorch/executorch#9625 · Opened Mar 25, 2025
Support RuntimeSpec Open

triaged

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

pytorch/executorch#9623 · Opened Mar 25, 2025
Enumerated shape support Open

triaged

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

pytorch/executorch#9622 · Opened Mar 25, 2025
Support reshapeFrequency runtime spec Open

triaged

Difficulty 5/5 Over a week Newbie friendliness 30/100

pytorch/executorch#9619 · Opened Mar 25, 2025
CoreML quantization is supported by PyTorch flows (PT2E). Open

triaged

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

pytorch/executorch#9617 · Opened Mar 25, 2025
Windows build failure: Failed to query buck for sources. Open

module: build/install module: user experience

pytorch/executorch#9616 · 15 comments · 1 assignee · Opened Mar 25, 2025
A supported ANE-friendly llama model with good out-of-the-box performance and accuracy. Open

triaged

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

pytorch/executorch#9615 · Opened Mar 25, 2025
All GA models are supported by CoreML and have similar performance to using CoreML via torch.export Open

triaged

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

pytorch/executorch#9614 · Opened Mar 25, 2025
All GA models export to CoreML via. torch.export with the same performance and user experience as torch.jit.trace Open

triaged

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

pytorch/executorch#9610 · Opened Mar 25, 2025
[Request help] Failed running call_function <built-in function getitem> Open

module: user experience

Difficulty 4/5 3-5 days Newbie friendliness 42/100

pytorch/executorch#9567 · 3 comments · Opened Mar 25, 2025
Model can't inference for Llama3.2-1B when use -d fp16 to convert pte Open

module: xnnpack triaged

pytorch/executorch#9534 · 4 comments · 1 assignee · Opened Mar 24, 2025
[CoreML] support palletization in PT2E flow Open

triaged

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

pytorch/executorch#9518 · 1 comment · Opened Mar 21, 2025
Document end-to-end quantization journey in ExecuTorch Open

triaged

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

pytorch/executorch#9515 · Opened Mar 21, 2025
[torchao/ExecuTorch] move embedding quantization to torchao Open

triaged

pytorch/executorch#9514 · 1 comment · 1 assignee · Opened Mar 21, 2025
ExecuTorch backends implement PT2E quantizer for PTQ/QAT Open

triaged

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

pytorch/executorch#9512 · Opened Mar 21, 2025
CoreML model works with torch.jit.trace, but not torch.export.export Open

module: coreml triaged

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

pytorch/executorch#9506 · 2 comments · Opened Mar 21, 2025
ExecuTorch Scalar to() supports fewer types than c10::Scalar, breaking source compatibility Open

good first issue module: runtime triaged

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

pytorch/executorch#9500 · 3 comments · Opened Mar 21, 2025
I want to understand the allocations made on STM32s by Executorch Open

module: runtime triaged

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

pytorch/executorch#9491 · 6 comments · Opened Mar 21, 2025
Run arm tests in OSS CI unittest-buck Open

module: arm triaged

pytorch/executorch#9476 · 1 comment · 1 assignee · Opened Mar 20, 2025
Support exporting QNN models with Python wheels out-of-the-box Open

module: build/install partner: qualcomm

pytorch/executorch#9474 · 1 comment · 2 reactions · 1 assignee · Opened Mar 20, 2025
KernelCall failed at instruction 0:16 in operator aten::le.Tensor_out: 0x12 Open

module: kernels

pytorch/executorch#9433 · 3 comments · 2 assignees · Opened Mar 20, 2025
Recipe and Input class definition for executorch.export API Open

module: exir triaged

pytorch/executorch#9366 · 2 comments · 1 assignee · Opened Mar 18, 2025
Qwen2.5-0.5b SpinQuant export .pte fail Open

need-user-input

Difficulty 4/5 3-5 days Newbie friendliness 28/100

pytorch/executorch#9353 · 5 comments · Opened Mar 18, 2025
Is the QNN backend support the model of Llama 3.2 3B instead of XNNPACK？ Open

module: qnn need-user-input partner: qualcomm

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

pytorch/executorch#9311 · 12 comments · Opened Mar 17, 2025
Start tracking drift between main and viable/strict Open

module: build/install module: ci

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

pytorch/executorch#9277 · Opened Mar 14, 2025
Add Gemma 3 to etLLM Open

module: examples

pytorch/executorch#9250 · 3 reactions · 1 assignee · Opened Mar 14, 2025
Vectorize optimized_portable_ops versions of portable ops? Open

actionable module: kernels

pytorch/executorch#9241 · 16 comments · 1 assignee · Opened Mar 13, 2025
torch._check_is_size is not being recognized by CoreML partitioner Open

enhancement module: coreml triaged

pytorch/executorch#9213 · 3 comments · 1 assignee · Opened Mar 13, 2025
Convert model.safetensors in order to be able to execute it with ExecuteTorch: how to prepare the example input and dynamic shape information? Open

module: user experience

pytorch/executorch#9180 · 1 comment · 1 assignee · Opened Mar 12, 2025
Vulnerability in the @babel/helpers dependency of ReactNative LLaMA App Open

module: reactnative

Difficulty 2/5 1-3 hours Newbie friendliness 50/100

pytorch/executorch#9179 · 1 comment · Opened Mar 12, 2025
Vulnerability in the @babel/runtime dependency of React Native LLaMA App Open

module: reactnative

Difficulty 1/5 Under an hour Newbie friendliness 45/100

pytorch/executorch#9178 · 1 comment · Opened Mar 12, 2025
Improve clarity for flattened graph inputs Open

module: exir module: user experience triaged

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

pytorch/executorch#9132 · 2 comments · Opened Mar 11, 2025
StablediffusionV2.1 on MI15 device Open

module: qnn triaged

pytorch/executorch#9080 · 1 assignee · Opened Mar 10, 2025
Dynamic Parameters for Mediatek Delegate Open

partner: mediatek triaged

pytorch/executorch#9035 · 1 comment · 2 assignees · Opened Mar 7, 2025
Refactor binary op partitioner configs under binary op config class Open

good first issue module: xnnpack triaged

pytorch/executorch#9024 · 9 comments · 1 reaction · 1 assignee · Opened Mar 6, 2025
Build pip wheel and validate AOT workflow on different backends & host environments in CI Open

module: build/install triaged

pytorch/executorch#9019 · 4 comments · 2 assignees · Opened Mar 6, 2025
SDPA custom op works without kv cach Open

module: llm triaged

pytorch/executorch#9014 · 1 assignee · Opened Mar 6, 2025
Freeing unpacked weights immediately after packing Open

module: xnnpack triaged

Difficulty 4/5 3-5 days Newbie friendliness 15/100

pytorch/executorch#9013 · Opened Mar 6, 2025
Shared activation memory with ExecuTorch Open

module: xnnpack triaged

Difficulty 5/5 Over a week Newbie friendliness 10/100

pytorch/executorch#9012 · Opened Mar 6, 2025
Setup Build-Size Check in CI for XNNPACK Dependency Open

module: xnnpack triaged

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

pytorch/executorch#9011 · 1 reaction · Opened Mar 6, 2025
Binary Size: Selective Build Open

module: build/install module: xnnpack triaged

Difficulty 5/5 Over a week Newbie friendliness 15/100

pytorch/executorch#9010 · 3 comments · Opened Mar 6, 2025
Reduce the number of files / directories at the root of the repository Open

module: user experience triaged

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

pytorch/executorch#8966 · Opened Mar 5, 2025
Replace remaining uses of linearize_access_indexes for broadcasting with BroadcastIndexesRange Open

module: kernels triaged

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

pytorch/executorch#8965 · 1 comment · Opened Mar 5, 2025
Enable ExecuTorch Tensor to store arbitrary resources Open

module: runtime triaged

pytorch/executorch#8939 · 1 assignee · Opened Mar 4, 2025
`torchao:` quantization schemes can't find ao lib Open

module: quantization triaged

Difficulty 3/5 1-2 days Newbie friendliness 35/100

pytorch/executorch#8937 · 5 comments · Opened Mar 4, 2025
Error running .pte model with executor_runner Open

module: runtime triaged

pytorch/executorch#8923 · 7 comments · 1 assignee · Opened Mar 4, 2025
Memory Profiling in DevTools Open

module: devtools triaged

pytorch/executorch#8911 · 6 comments · 1 reaction · 1 assignee · Opened Mar 4, 2025
[Android] Flatten data structure like dict in arg types Open

module: android triaged

pytorch/executorch#8905 · 1 assignee · Opened Mar 3, 2025
XNNPack configurations can be complicated to get right Open

module: user experience module: xnnpack triaged

pytorch/executorch#8884 · 14 comments · 3 reactions · 1 assignee · Opened Mar 3, 2025
Temperature Settings in Android llama demo (Mediatek) Open

module: android module: llm module: mediatek partner: mediatek triaged

pytorch/executorch#8878 · 5 comments · 3 assignees · Opened Mar 3, 2025

pytorch/executorch

Get new issues in your inbox