pytorch/executorch
On-device AI across mobile, embedded and edge for PyTorch
ExecuTorch helps developers deploy their AI models directly onto devices like smartphones, smart glasses, or microcontrollers, ensuring privacy, performance, and portability. It takes a trained PyTorch model and converts it into an optimized `.pte` file that can run efficiently on various hardware. This is for software engineers and machine learning practitioners who build and deploy AI-powered features for consumer electronics, IoT devices, or industrial edge applications.
4,374 stars. Actively maintained with 371 commits in the last 30 days. Available on PyPI.
Use this if you need to run AI models directly on user devices or embedded hardware, keeping data private and processing fast without cloud dependency.
Not ideal if your AI models only run on cloud servers or high-performance data center GPUs.
Stars
4,374
Forks
870
Language
Python
License
—
Category
Last pushed
Mar 13, 2026
Commits (30d)
371
Dependencies
25
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pytorch/executorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Related frameworks
catalyst-team/catalyst
Accelerated deep learning R&D
z-mahmud22/Dlib_Windows_Python3.x
Dlib compiled binaries (.whl) for Python 3.7-3.14 and Windows x64
mit-han-lab/mcunet
[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2:...
gigwegbe/tinyml-papers-and-projects
This is a list of interesting papers and projects about TinyML.
ai-techsystems/deepC
vendor independent TinyML deep learning library, compiler and inference framework microcomputers...