The official ExecuTorch docker image.
Maintained by: openKylin RISC-V SIG.
Where to get help: openKylin RISC-V SIG, openKylin.
ExecuTorch is PyTorch's unified solution for deploying AI models on-device—from smartphones to microcontrollers—built for privacy, performance, and portability. It powers Meta's on-device AI across Instagram, WhatsApp, Quest 3, Ray-Ban Meta Smart Glasses, and more.
Deploy LLMs, vision, speech, and multimodal models with the same PyTorch APIs you already know—accelerating research to production with seamless model export, optimization, and deployment. No manual C++ rewrites. No format conversions. No vendor lock-in.
The tag of each ExecuTorch docker image is consist of the complete software stack version. The details are as follows
| Tag | Currently | Architectures |
|---|---|---|
| 1.3.1-ok20 | ExecuTorch 1.3.1 on openKylin 2.0 | amd64,arm64,riscv64 |
Ensure that you have Docker installed, or are using Docker for Linux containers if on Windows.
Obtain the ExecuTorch ecosystem docker image. There are two ways to do this:
Pull the pre-built Docker image
# From DockerHub
docker pull openkylin/executorch
# From Quay
docker pull quay.io/openkylin/executorch
Clone the source repository. Navigate to the AI/executorch folder and build the image locally with the following command.
docker build . -t openkylin/executorch
docker run -it openkylin/executorchIf you have any questions or want to use some special features, please submit an issue or a pull request on openkylin-docker-images.
Content type
Image
Digest
sha256:465df13b3…
Size
4.1 GB
Last updated
3 months ago
docker pull openkylin/executorch