-
Notifications
You must be signed in to change notification settings - Fork 9
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
LiteRT runtime build not working for Linux+Aarch64 #5
Comments
Bummed that I cannot install on the Pi 4 running But the docs do still say to use
|
yeah..... it's really curious how a library aimed for edge-runtime don't have an arm64 build available in the end, I build it myself using that ci script and it is working 🙃 ai_edge_litert_nightly-1.0.1.dev20241024-cp311-cp311-linux_aarch64.zip well, use it at your own discretion 😅 |
Another example where this is needed is for macOS ARM64 local development within containers-- this requires an ARM64 Linux wheel when installing into the container. |
There is no aarch64 linux wheel for ai-edge-litert.
https://pypi.org/project/ai-edge-litert/#files
For tensorflow there is e.g. CPython 3.11 manylinux: glibc 2.17+ ARM64
https://pypi.org/project/tensorflow/#files
It appears not to be possible to build natively for aarch64+linux from source (using the ci/build_pip_package_with_bazel.sh script):
How to reproduce on Linux+Aarch64:
./ci/build_pip_package_with_bazel.sh
Building TFL runtime in tensorflow on Linux+Aarch64 works:
./tensorflow/lite/tools/pip_package/build_pip_package_with_cmake.sh
The text was updated successfully, but these errors were encountered: