QNNPACK for TensorFlow Lite

I am looking for an alternative for QNNPACK to execute quantized DNN effectively on CPU, ARM-based devices. In other words, what is the recommended approach to effectively interpret quantized NN? Is there QNNPACK available for TensorFlow Lite?

Please can I have some examples?

Thank you.

Hi @Jack_Daniels ,
You can use XNNPACK instead of QNNPACK for quantization. As well for ARM specific deveices you can directly use the NEON instruction set through optimized libraries such as CMSIS-NN or Arm Compute Library.
For interpreting the quantized tool you can use the Visualization tools like TensorBoard or Netron.
QNNPACK is available in TFLite.
Thank You