Give feedback

How would you rate this Learning Path?

Review frequently asked questions

AI-assisted

These FAQs were drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.

Close
?
How do I confirm that KleidiAI is used at runtime?
MLAS checks CPU capabilities at runtime and dispatches to KleidiAI when SME2 is present. When enabled, GEMM and convolution operators use ArmKleidiAI kernels instead of the default MLAS paths.
Which ONNX Runtime version should I use?
Use ONNX Runtime v1.23.2.
Which Android NDK version should I use for the build?
Use Android NDK r26b or later. NDK r27 or later is recommended for the latest SME2 toolchain support.
Where should I place the ResNet-50 v2 model files on the device?
Copy the archive to /data/local/tmp and extract it there.
What should I check if SME2 acceleration doesn’t appear to be used?
Verify the Android device supports SME2, because MLAS enables KleidiAI only when SME2 is detected. If SME2 is unavailable, MLAS falls back to its default kernels (for example, Neon), and you can still profile that baseline.

Share

Tell others about this Learning Path.

Back
Return to Mobile, Graphics, and Gaming